Вакансии

🔹 Design and build scalable, reliable backend services. 🔹 Drive architecture and technical research.

Location: Austria; France; Germany; Italy; Netherlands; Poland; Spain; United Kingdom Why Kimchi? Great models are raw ingredients. Kimchi is what happens when you ferment them with good engineering. We started inside CAST AI helping companies run LLMs on their own Kubernetes clusters; today we run our own coding harness on any model you pick, and the router deciding which model answers each request is ours too. The Auto Router Our promise is one enforcement layer for your AI: budgets, spend attribution, and model routing, applied before a request ever hits a model. The Auto Router makes the call: for every request, which model serves it. Eight open-source models whose input prices span more than 20×, cached input up to 50× cheaper than fresh, frontier providers on customers' own keys, and a coding agent that fires hundreds of requests before its task is done. Frontier-level task success at a fraction of the token cost: that sentence is the product, and it stays true only if the model inside the router keeps getting better. That model is yours. Made by Cast AI — a Miami-headquartered, globally distributed team across 34 countries that hit unicorn status in January 2026 with a $50B+ backed investment pushing its valuation past $1 billion. About the role Every request gets a decision: which model serves it. This is an applied-ML seat, not an infrastructure one. Platform engineers own the proxy, the streaming path, and the fleet. You own the model inside them: the training data, the objective, the evaluation, and the iteration loop that ships a better router every cycle. The problem: routing is a prediction problem wearing a product's clothes. For every request you predict the quality each candidate model would deliver, what it would cost, and how fast it would decode, and you have to be right enough, in aggregate, that the savings are real and the quality never dips below frontier. The data is messy: rollout outcomes from benchmark harnesses, per-request records from the live fleet, override signals, and token streams whose speed depends on the serving concurrency at the moment. Speed itself is a correctness variable: on deadline-bound agentic work, a model that decodes three times slower doesn't do the same work slower, it does less work. That's why naive cost-per-token objectives quietly optimize for the wrong thing. And the bar for evidence is high: a router change ships only after production-parity evaluation with error bars, then gets held to its numbers in live traffic. Stack: Python; PyTorch; SQL at scale (ClickHouse); OpenAI- and Anthropic-compatible LLM APIs; benchmark and rollout harnesses (RouterBench-class); GitLab CI. Requirements You've spent 5+ years in applied ML or ML research, and you've trained, evaluated, and shipped models that make real-time decisions (ranking, recommendation, bandits, pricing, or LLM routing) and you can tell that story with receipts. Strong Python and SQL at scale: you can pull, clean, and interrogate millions of request-level records without waiting on anyone. You know the difference between a model that got better and an eval that got easier. You have real opinions about what LLM benchmarks measure, agentic harnesses included. You know enough serving reality (TTFT, decode speed, batching, prefix caching, concurrency) to model the objective honestly. You instrument before you optimize, error bars and all. A wide mandate excites you more than it unsettles you. Nice to haves You've worked on LLM routing specifically: RouterBench-class evals, cost/quality/latency Pareto fronts. Calibration, abstention, or conformal methods in production decision systems. You've run online A/B loops with drift monitoring on a model that touches real money. Responsibilities Own the routing model end to end: features, objective, training, calibration, and release cadence. Iterate it like a product, not a research artifact. Build the evaluation that gates every change: production-parity benchmarks, router-vs-router comparisons, holdouts by task family, error bars on pass rates. Nothing ships on vibes. Turn fleet data into training signal: per-request outcomes from production, benchmark rollouts, and override feedback, with failure categorization (infra vs task) so poisoned labels never reach the policy. Model the objective the user actually experiences: task success × token cost × wall-clock speed under the real concurrency regime, with cached-input economics in the picture. Run the online loop: shadow, A/B, full rollout, drift monitoring, retrain. When production disagrees with your offline eval, you find out why before the next ship. Push the frontier where it pays: calibrated decisions, abstention under uncertainty, speed-aware routing. We experiment on what a router should be, not just which model it picks today. Partner with platform engineers on instrumentation: the features and labels recorded per request (decode speed first-class among them) and the experiments the data path must support. What’s in it for you? Competitive salary (depending on the level of experience). Enjoy a flexible, remote-first global environment. Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology Equity options. Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks. Spend 10% of your work time on personal projects or self-improvement. Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills. Annual hackathon to spark new ideas and strengthen team bonds. Team-building budget and company events to connect with your colleagues. Equipment budget to ensure you have everything you need. Extra days off to help maintain a healthy work-life balance. Hiring process Screening call with Recruiter Hiring Manager interview Technical interview (system design) Live coding Culture Check interview with an executive As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr. Please note that Cast AI does not provide any form of visa sponsorship/work permit. #LI-Remote

Location: Austria; France; Germany; Italy; Netherlands; Poland; Spain; United Kingdom Why Kimchi? Great models are raw ingredients. Kimchi is what happens when you ferment them with good engineering. We started inside CAST AI helping companies run LLMs on their own Kubernetes clusters; today we run our own coding harness on any model you pick, and we run the models underneath it ourselves. Kimchi Inference One API line and a customer's existing client just works: DeepSeek, GLM, Kimi, MiniMax, Nemotron served serverless from our own GPU fleet (OpenAI- and Anthropic-compatible, pay per token, spend visible per user, team, and key). When control matters, the same models run on the customer's own cluster instead. Behind that one line sits the machinery you'll own: SGLang and vLLM engines, B300 nodes, a shared cluster filesystem that holds every checkpoint exactly once, KV caches riding coding traffic with heavy prefix reuse, and the benchmark harness that gates every change we ship. Made by Cast AI — a Miami-headquartered, globally distributed team across 34 countries that hit unicorn status in January 2026 with a $50B+ backed investment pushing its valuation past $1 billion. About the role Throughput. Latency. Cold starts. Cost per token. Move those four numbers in the right direction and two things happen: customers get faster, cheaper inference, and our margins improve. That's the entire thesis of this role. Every loader you tune, every scheduler decision you land, every kernel you stare at shows up in a customer's p99 and on our P&L. Your mandate is the inference stack's optimization, whatever it takes, and the technical direction of how we optimize it is yours to argue with data. The problem: the checkpoints run 0.3-1.5 TB, and the "right" serving configuration depends on traffic shape, sequence-length distribution, batch dynamics, GPU SKU, memory bandwidth, and quantization tolerance, all variables that shift week to week. Most teams pick a configuration once, over-provision GPUs, and absorb the cost. We don't: we took Kimi-K3 (1.5 TB) from over an hour cold-to-serving to under twelve minutes with a shared filesystem, O_DIRECT weight loaders, and node-local JIT caches, and we're nowhere near done. Prefill/decode disaggregation and tiered KV caches are next. Stack: Python; SGLang; vLLM; TensorRT-LLM; PyTorch; fastsafetensors; CUDA-adjacent tooling; Kubernetes; virtiofs shared filesystems; ClickHouse; OpenTelemetry; Prometheus; Grafana; GitLab CI. Requirements You've built real ML systems for 5+ years, and your portfolio shows depth in inference or training infrastructure, not just model training notebooks. Your Python is production-grade: services, not scripts. You've run vLLM, SGLang, or TensorRT-LLM for real, and you have a working mental model of why an engine performs the way it does on a given GPU. You've measured quantization regressions, not just compression ratios. Multi-GPU and multi-node setups hold no fear: tensor and expert parallelism, collective communication, and their practical failure modes. You know where the bytes live (page caches, O_DIRECT, network filesystems under terabyte-scale reads) and how fast they move. You instrument before you optimize, and you can tell a real win from a benchmark artifact. A wide mandate excites you more than it unsettles you. Nice to haves You've worked on LLM routing specifically: RouterBench-class evals, cost/quality/latency Pareto fronts. Calibration, abstention, or conformal methods in production decision systems. You've run online A/B loops with drift monitoring on a model that touches real money. Responsibilities Push throughput. Continuous batching, chunked prefill, speculative decoding with draft models, CUDA-graph capture, and scheduler tuning across the engine fleet. Find the ceiling on each GPU SKU, then raise it. Cut latency. Attack TTFT and inter-token latency separately; profile to find the actual bottleneck (compute, memory bandwidth, scheduling, storage, or network) and fix it, not the one you assumed. Get more out of the KV cache. Hierarchical and paged attention, prefix caching on heavy-reuse coding traffic, eviction policies, quantized KV. A lot of the unrealized throughput lives here, and you'll own it. Kill cold starts. Weight loaders (O_DIRECT, fastsafetensors-class), JIT and compile caches, shared-filesystem read paths. A 1.5 TB checkpoint has no business taking an hour to reach serving. Quantize without regressing quality. INT8/INT4, FP8/FP4 across weights, activations, and KV, measured on real workloads, not just perplexity benchmarks. Scale across nodes. Distributed inference topologies, network-aware placement, prefill/decode disaggregation, checkpointing strategies that don't bottleneck on storage or interconnect. Set the technical direction. Decide what we benchmark, what we adopt, and what we build ourselves. Bring the team along with strong writeups and reproducible experiments. What’s in it for you? Competitive salary (depending on the level of experience). Enjoy a flexible, remote-first global environment. Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology Equity options. Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks. Spend 10% of your work time on personal projects or self-improvement. Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills. Annual hackathon to spark new ideas and strengthen team bonds. Team-building budget and company events to connect with your colleagues. Equipment budget to ensure you have everything you need. Extra days off to help maintain a healthy work-life balance. Hiring process Screening call with Recruiter Hiring Manager interview Technical interview (system design) Live coding Culture Check interview with an executive As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr. Please note that Cast AI does not provide any form of visa sponsorship/work permit. #LI-Remote

Задачи: — Работать с членами проектной команды на этапах требований и проектирования для разработки стратегий тестирования, планов тестирования и тест-кейсов. — Предоставлять экспертные рекомендации и разрабатывать стратегии и планы тестирования для всех рекомендуемых типов тестирования, обеспечивая покрытие с помощью матрицы трассировки требований. — Разрабатывать и выполнять тестовые сценарии, автоматизированные и ручные тестовые скрипты, участвовать в подготовке тестовых данных. — Управлять выявлением дефектов, их разрешением и отслеживанием. — Использовать DevOps-инструменты для предоставления отчетов о статусе тестирования и сводных отчетов по проблемам. — Писать стандартные операционные процедуры по обеспечению и контролю качества. — Тесно сотрудничать с владельцем продукта, менеджером проекта, бизнес-аналитиками и системными аналитиками для обеспечения соответствия QA-результатов объему проекта и срокам. — Участвовать в совещаниях по обзору дефектов и предоставлять анализ по запросу. — Проводить функциональное и нефункциональное тестирование. — Проводить тестирование на соответствие AODA (WCAG 2.0). — Тестировать мобильные приложения. — Проводить тестирование безопасности. — Управлять тестовыми данными. — Управлять тестовой средой. — Проводить тестирование миграции данных и другие виды тестирования по необходимости. — Поддерживать других членов QA-команды в случае их отсутствия. — Информировать менеджеров проектов и команду IAM о стратегиях, планах и результатах тестирования. Требования: — Экспертные знания в области автоматизации тестирования (40% времени): проектирование, внедрение и поддержка фреймворков автоматизации тестирования (Selenium, Appium, BrowserStack, Sauce Labs, JUnit и др.). — Навыки программирования на Java, Python, JavaScript, NestJS с возможностью писать надежные и переиспользуемые скрипты. — Опыт автоматизации тест-кейсов для сложных масштабных веб-приложений, мобильных приложений и RESTful API с высоким покрытием. — Опыт интеграции автоматизированных тестов в CI/CD пайплайны (GitHub Actions, Azure DevOps и др.). — Опыт автоматизированного тестирования производительности и нагрузочного тестирования (JMeter, Python Locust и др.). — Опыт автоматизации кросс-браузерного и кросс-платформенного тестирования. — Навыки управления тестовыми данными для автоматизированных тестов. — Опыт разработки и выполнения стратегий тестирования, планов и тест-кейсов на основе требований, пользовательских историй и критериев приемки. — Глубокое понимание функционального и нефункционального тестирования, включая безопасность, удобство использования и нагрузочное тестирование. — Опыт работы с баг-трекинговыми системами (Jira или аналогичные). — Опыт анализа покрытия тестирования и улучшения тест-кейсов. — Опыт ручного тестирования, особенно для исследовательского тестирования и сложных случаев. — Знание систем контроля версий (Git, SVN и др.). — Опыт тестирования API с использованием Postman, SoapUI и др. — Навыки работы с базами данных и SQL для проверки данных. — Знакомство с облачными платформами (Azure, AWS) и виртуализацией (Docker, Kubernetes). — Опыт тестирования веб и мобильных приложений, включая цифровые кошельки для идентификации. — Знание практик тестирования безопасности, OWASP Top 10, безопасного кодирования и автоматизированных инструментов. — Понимание стандартов цифровой идентификации и технологий (W3C VC, DIDs, JSON-LD, OpenID Connect, OAuth2, JWT, JWS, PCTF, NIST, eIDAS). — Навыки командной работы и коммуникации с разработчиками, DevOps, аналитиками и менеджерами. — Опыт работы в Agile/Scrum средах. Условия: — Удаленная работа из Канады.

Задачи: — Проводить ручное функциональное, интеграционное и системное тестирование. — Разрабатывать и поддерживать тестовую документацию, работать с дефектами, анализировать и воспроизводить пользовательские ошибки. — Проводить review артефактов тестирования и совершенствовать процессы тестирования. — Автоматизировать функциональное тестирование на Python. Требования: — Опыт более 5 лет. — Не менее 3 лет практического опыта создания тест-кейсов и сценариев, подготовки и поддержки тестовой документации в TestRail, Zephyr или Xray. — Применение методов тест-дизайна. — Не менее 2 лет опыта ручного тестирования REST API с Postman, Insomnia или curl, проверки схем JSON Schema и OpenAPI и валидации бизнес-логики. — Опыт автоматизации backend-тестов на Python с pytest и UI-тестов на Playwright, включая интеграцию с CI. — Практический опыт тестирования систем с Apache Kafka, включая проверку порядка и гарантий доставки сообщений, тем, партиций и схем в Schema Registry. — Опыт интеграционного, системного и UAT-тестирования, подготовки end-to-end сценариев и тестовых окружений, согласования критериев приёмки. — Навыки тестирования БД и написания SQL-запросов. — Опыт работы с PostgreSQL, MySQL, Oracle, MongoDB и Redis, проверки целостности данных и миграций. — Опыт работы с Docker, GitLab CI, Kubernetes, kubectl и Helm, а также в Linux: написание bash/sh-скриптов, настройка сетевых параметров, мониторинг процессов и отладка тестовых стендов. Условия: — Формат: удалённо, полная занятость, оформление по ГПХ. — Требуется гражданство РФ.

Задачи: — Проектировать, разрабатывать и поддерживать качественные программные решения, соответствующие бизнес-целям. — Сотрудничать с кросс-функциональными командами для определения, проектирования и выпуска новых функций. — Писать чистый, поддерживаемый и эффективный код, следуя лучшим практикам. — Отлаживать и решать сложные технические проблемы в сжатые сроки. — Участвовать в код-ревью и способствовать улучшению процессов команды. Требования: — Опыт работы в качестве Software Engineer не менее 3 лет. — Владение Java. — Глубокое понимание принципов разработки ПО, включая ООП, паттерны проектирования и масштабируемую архитектуру. — Опыт работы с RESTful API, микросервисной архитектурой и облачными платформами (AWS, Azure, GCP). — Знание реляционных и нереляционных баз данных (SQL, MongoDB). — Уверенное владение Git и рабочими процессами контроля версий. — Свободное владение английским языком, отличные коммуникативные и командные навыки. — Будет преимуществом: опыт работы с контейнеризацией (Docker, Kubernetes), знание CI/CD и практик DevOps. — Опыт в финтех-индустрии или банковском ПО. Условия: — Конкурентная зарплата и полный пакет социальных льгот. — Возможность работать на передовой финтех-платформе. — Динамичная и поддерживающая рабочая среда с возможностями профессионального роста. — Влияние на успех клиентов и развитие финтех-экосистемы.

Задачи: — Писать и поддерживать автотесты на Java. — Проводить ручное, интеграционное и регрессионное тестирование. — Тестировать API и взаимодействие микросервисов. — Анализировать требования и тестовое покрытие. — Разрабатывать инструменты автоматизации и работать с CI/CD. Требования: — Коммерческий опыт написания автотестов на Java от 2 лет и общий опыт веб-тестирования от 4 лет. — Подойдёт сочетание 2 лет автоматизации и 2 лет ручного тестирования. — Опыт работы с REST API, SQL на уровне сложных запросов. — Опыт с Jenkins или GitLab CI. — Опыт с Kafka или RabbitMQ. — Опыт с WireMock или аналогами. — Опыт работы с инфраструктурой и кешами. — Стек: Docker, Kubernetes или OpenShift, Redis или Hazelcast. Условия: — Работа в Санкт-Петербурге, большую часть времени удалённо, офис раз в две недели. — Гибкий график по договорённости с командой. — ДМС со стоматологией с первых дней. — Оплата профильных курсов и конференций. — Квартальная премия по KPI. — Доход обсуждается на интервью.

Задачи: — Разработка и поддержка автотестов для web-приложений на Java, Selenium/Selenide и REST Assured. — Анализ функциональных и нефункциональных требований, разработка тест-кейсов. — Интеграция автотестов в CI/CD, участие в код-ревью, поддержка и развитие фреймворка автоматизации. — Тестирование асинхронных сервисов через брокеры сообщений, оптимизация и рефакторинг автотестов. Требования: — Высшее образование и коммерческий опыт автоматизированного тестирования более 3 лет. — Уверенное знание Java Core, опыт разработки UI- и API-автотестов. — Знание TestContainers, REST Assured, Selenium/Selenide/Playwright. — Знание Maven или Gradle, JUnit 5 или TestNG, процессов тестирования и техник тест-дизайна. — Опыт работы с TMS и баг-трекерами, понимание ООП и паттернов проектирования, включая Page Object и Page Factory. — Опыт работы с PostgreSQL, MySQL или Oracle и написания SQL-запросов средней сложности. — Опыт настройки CI/CD-пайплайнов, работы с Kafka и/или RabbitMQ, ELK/Kibana/Grafana, Docker и Kubernetes. — Понимание работы Istio-proxy и умение читать логи Kubernetes. — Будет плюсом: Kotlin, Linux, настройка тестовых окружений, BDD (Cucumber, JBehave), нагрузочное тестирование, MongoDB и Redis. Условия: — Удалённая работа, полная занятость или проектная работа. — Оформление по ГПХ. — Локация и гражданство: РФ или РБ.

Задачи: — Работать с широким техническим стеком, включая AWS инфраструктуру, Kubernetes, распределённые системы, инструменты наблюдения, инструменты деплоя и внутренние платформы для разработчиков. — Понимать взаимодействия систем и сервисов, выявлять узкие места и создавать платформенные возможности для повышения надёжности и продуктивности разработчиков. — Проектировать, строить и эксплуатировать облачную инфраструктуру и платформенные сервисы на базе AWS. — Создавать переиспользуемые внутренние платформенные возможности для улучшения процессов разработки, деплоя и эксплуатации сервисов. — Работать с AWS, Kubernetes, инфраструктурой как код (IaC), CI/CD, наблюдаемостью и распределёнными системами. — Сотрудничать с продуктовыми инженерами для выявления повторяющихся потребностей и превращать их в масштабируемые платформенные решения. — Оценивать взаимодействия систем, выявлять риски и неэффективности, инициировать улучшения. — Повышать надёжность, производительность, доступность и поддерживаемость производственных систем. — Определять и продвигать платформенные практики (SLO, мониторинг, реагирование на инциденты, готовность к эксплуатации). — Инструментировать, отлаживать и улучшать сервисы и инфраструктуру, включая сервисы на TypeScript. — Руководить техническими инициативами от определения проблемы до внедрения и принятия. — Сообщать о компромиссах, рисках и прогрессе заинтересованным сторонам. — Наставлять инженеров в создании надёжных и масштабируемых систем. — Участвовать в дежурствах и реагировании на инциденты. Требования: — Опыт работы в области разработки программного обеспечения или инфраструктуры не менее 5 лет. — Глубокий опыт работы с AWS в продуктивных средах. — Опыт работы с облачной инфраструктурой, распределёнными системами и проектированием систем. — Опыт создания внутренних платформ, инструментов для разработчиков или общих сервисов. — Практический опыт работы с Kubernetes и инфраструктурой как код (Terraform будет плюсом). — Сильные навыки программирования и умение отлаживать продуктивные системы (TypeScript будет плюсом). — Опыт работы с CI/CD и автоматизированными процессами деплоя. — Опыт работы с инструментами наблюдения (метрики, логи, трассировки, алерты, SLO). — Способность анализировать сложные системы и понимать взаимодействия между компонентами. — Опыт руководства техническими инициативами с участием нескольких заинтересованных сторон. — Сильные коммуникативные навыки и умение работать в команде. Условия: — Работа удалённо из провинций Британская Колумбия или Онтарио, Канада. — Годовая зарплата от 123,750 до 165,000 CAD. — Возможность участия в программе опционов на акции компании. — Медицинская страховка, стоматологическая страховка, страхование жизни, страхование от несчастных случаев и инвалидности. — Программа поддержки при стихийных бедствиях. — Приложения для здоровья и благополучия. — Оплачиваемый отпуск по уходу за ребёнком, оплачиваемый отпуск, включая праздничные и больничные дни. — Единовременная выплата на обустройство домашнего офиса. — Пенсионный план. — Финансовое планирование. — Бюджет на обучение и развитие. Компания Lattice занимается созданием платформы для успеха сотрудников и компаний, предоставляя инструменты для обзоров эффективности, опросов вовлечённости, обратной связи, постановки целей и планирования карьеры. Компания поддерживает равные возможности и инклюзивность в найме и работе.

Задачи: — Проектирование, разработка и поддержка фреймворка и библиотек для автоматизации тестирования — Разработка инструментов автоматизации установки и настройки продукта под разные среды выполнения — Разработка и автоматизация сценариев тестирования продукта — Интеграция инструментов тестирования в процесс CI/CD (GitLab CI) — Разработка и проведение нагрузочного тестирования продукта Требования: — Обязательное владение стеком: Python (разработка скриптов и утилит), Pytest (написание тестовых сценариев и фикстур), Docker (сборка образов и оркестрация окружений через docker-compose) — Глубокое знание GitLab CI: опыт написания пайплайнов для автоматизации прогонов тестов, настройки артефактов, параллелизации задач и управления динамическими средами — Работа с Git: уверенное владение ветвлением, стратегиями ревью и командной работой в репозиториях — Опыт применения AI-агентов в повседневной работе для ускорения написания кода, генерации тестовых сценариев и анализа логов Будет плюсом: — Опыт с Kubernetes: развертывание тестовых стендов с помощью Helm и работа с кластерами (k3s/minikube) — Опыт написания сценариев на k6 (Go/JS), настройка дашбордов и алертов в Observability Stack (Grafana, Prometheus, Loki, Alloy) — Опыт с SIEM или колончатыми СУБД (как ClickHouse) Условия: — Полная занятость — График: 5/2 — Формат работы: удалённо или гибрид или офис

Задачи: — Разработка и поддержка сервисов на C# и .NET — Работа с PostgreSQL, оптимизация запросов, поддержка схем данных — Реализация бизнес-логики расчётов, тарифов, начислений — Интеграции с внешними системами и государственными сервисами через API — Разработка модулей формирования отчётов, выгрузок, реестров — Поддержка очередей задач, асинхронных процессов, обмена данными между сервисами Требования: — Коммерческий опыт в сфере разработки на C# и .NET от 5 лет — Хорошее понимание ООП и паттернов проектирования — Практический опыт работы с PostgreSQL — Понимание и опыт применения CQRS и Event Sourcing в реальных проектах — Умение независимо формулировать и решать задачи — Работа через ИП Будет плюсом: — Опыт настройки CI/CD — Опыт работы с системами мониторинга и логирования — Знание и практика с RabbitMQ, gRPC — Опыт контейнеризации и оркестрации: Docker, Kubernetes Условия: — Удалённая работа, периодические встречи в видеоконференциях для синхронизации — Гибкий рабочий день: 6-8 часов в удобное для вас время — Фокус на качестве кода и архитектуре, без гонки за сроками

Требуется Главный SRE/DevOps-инженер уровня Senior или Senior+ для работы в часовом поясе Москвы с зарплатой от 220 000 рублей и локацией в России. Кандидат должен обладать глубокими знаниями в области S3/Object Storage и архитектуры распределенного хранения данных, а также иметь опыт сопровождения Kubernetes-платформ. Важен практический опыт эксплуатации компонентов Data Lake, таких как Apache Spark, Airflow, Flink, Kafka и Apache Iceberg, а также опыт работы с MinIO и другими решениями Object Storage. В обязанности входит сопровождение и эксплуатация платформы Data Lake, поддержка инфраструктуры S3/Object Storage, мониторинг и устранение инцидентов, решение проблем с производительностью платформы и систем хранения, сопровождение Kubernetes и компонентов Data Lake, проведение анализа причин инцидентов (RCA) и постмортем, автоматизация эксплуатационных процессов, взаимодействие с командами Data Engineering и инфраструктуры, а также сопровождение Big Data Platform. Требования включают экспертные навыки администрирования Linux, опыт работы с высоконагруженными распределенными системами, понимание механизмов репликации, erasure coding, согласованности данных и отказоустойчивости. Необходимы навыки устранения проблем, связанных с CPU, RAM, сетью, дисковыми операциями, задержками и пропускной способностью, опыт работы с инструментами наблюдаемости (Prometheus, Grafana, alerting, анализ логов), а также умение автоматизировать задачи с помощью Ansible, Terraform, Bash и Python. Кандидат должен хорошо разбираться в управлении инцидентами и проблемами, владеть практиками SRE, а также иметь опыт проведения RCA, постмортем анализа и повышения надежности платформ.

Задачи: — Самостоятельное выявление угроз, анализ рисков, расследование инцидентов и внедрение технических мер защиты. — Полный цикл Incident Response: Detect → Analyze → Assess Risk → Contain → Remediate → Verify → Document. Требования: — Опыт в Cybersecurity / Information Security от 3 лет. — Уверенное администрирование Linux, Server Hardening. — Глубокое понимание TCP/IP, DNS, HTTP/HTTPS, TLS, VPN. — Практический опыт с Firewall, WAF, IDS/IPS, SIEM, Cloudflare и DDoS Protection. — Vulnerability Management (Nessus, OpenVAS, Qualys), CVE/CVSS. — Web/API Security, OWASP Top 10. — Анализ логов, расследование Security Incidents, работа с IOC. — Управление доступом: RBAC, MFA, PAM, Least Privilege. — Автоматизация задач безопасности — Bash/Python. — Реальный опыт проектирования и внедрения Zero Trust / ZTNA, а не только теоретические знания. — Identity-based Access, Device Trust, Conditional Access, Microsegmentation. — Интеграция с IAM/SSO/IdP, контроль привилегированного доступа. — Опыт с Cloudflare Zero Trust, Teleport, CyberArk, Tailscale, Zscaler или аналогичными решениями. Будет преимуществом: — AWS/Azure/GCP Security, Kubernetes Security, Wazuh, Suricata, Pentest, Threat Modeling, ISO 27001, PCI DSS. Условия: — Локация: Пафос, Кипр (офис). — График: 09:00–18:00. — Зарплата: €6 000–8 000 / месяц. Важно: — Нанимающая компания не рассматривает граждан РФ. — Кандидаты без практического опыта внедрения Zero Trust / ZTNA не рассматриваются.

Location: Bangalore, India GitLab is the intelligent orchestration platform for DevSecOps. GitLab enables organizations to increase developer productivity, improve operational efficiency, reduce security and compliance risk, and accelerate digital transformation. More than 50 million registered users and more than 50% of the Fortune 100* trust GitLab to ship better, more secure software faster. The same principles built into our products are reflected in how our team works: we embrace AI as a core productivity multiplier, with all team members expected to incorporate AI into their daily workflows to drive efficiency, innovation, and impact. GitLab is where careers accelerate, innovation flourishes, and every voice is valued. Our high-performance culture is driven by our values and continuous knowledge exchange, enabling our team members to reach their full potential while collaborating with industry leaders to solve complex problems. Co-create the future with us as we build technology that transforms how the world develops software. * Fortune 500® is a registered trademark of Fortune Media IP Limited, used under license. Claim based on GitLab data. Fortune 100 refers to the top 20% ranked companies in the 2025 Fortune 500 list, published in June 2025. Fortune and Fortune Media IP Limited are not affiliated with, and do not endorse products or services of GitLab. An overview of this role We're looking for an Intermediate Site Reliability Engineer to join the Cells Infrastructure team in GitLab's Scale & Architecture organization. In this role, you'll help build and operate Cells, the architecture that lets GitLab.com scale horizontally. Cells splits GitLab.com into many independent units, each with its own application and data stack, behind a shared routing layer. This is a build-it-and-run-it role. You'll provision cells, route traffic to them, deploy them safely, and keep them reliable in production. You'll also help move customer organizations onto Cells, one of GitLab's most important scaling initiatives. What you'll do Operate Cells in production: join the on-call rotation, respond to incidents, lead post-incident reviews, and drive corrective actions to completion. Define and monitor service level objectives (SLOs) for routing and cell health, and build the dashboards, alerts, and runbooks behind them. Provision and operate cell infrastructure on Amazon Web Services (AWS) and Google Cloud Platform (GCP), including Kubernetes, networking, Identity and Access Management (IAM), PostgreSQL, Redis, and object storage. Develop infrastructure as code with Terraform, Helm, and GitOps tooling such as Argo CD. Operate and extend the global routing layer, built on Cloudflare Workers, Envoy, and a Go service backed by Cloud Spanner, and expand routing to more protocols and services. Improve the continuous integration and continuous delivery (CI/CD) pipelines behind ring-based deployments, covering promotion, database migrations, quality assurance validation, and rollback. Support organization migrations by preparing destination cells and helping with dry runs and production cutovers. Work with product teams to make their services cell-compatible, and write documentation so others can operate Cells with confidence. Take part in on-call or operational support where your team’s ownership model requires it. What you'll bring Professional experience running production infrastructure at scale on AWS, GCP, or both, including Kubernetes, along with strong Terraform and Helm skills. Proficiency in Go, or strong experience in another systems language and willingness to work in Go daily. Solid grounding in site reliability engineering (SRE) best practices: SLOs and error budgets, blameless post-incident reviews, reducing toil through automation, capacity planning, and designing for graceful degradation. Experience owning services in production, including on-call, incident response, and monitoring with tools such as Prometheus and Grafana. Practical knowledge of progressive delivery: how to roll changes safely across a fleet and how to roll them back. A strong understanding of distributed-systems fundamentals, such as request routing, proxies, consistency, and failure domains. Experience working effectively in distributed, all-remote teams: you default to asynchronous, written-first communication, document decisions in issues and merge requests, hand off work cleanly across time zones, and stay transparent about progress and blockers. Experience with Cloudflare, Spanner, Argo CD, TypeScript, or operating GitLab at scale is a plus, not a requirement. About the team Every team in our organization owns its services end to end, from design through on-call.We own the control plane that tracks cells and decides where each request belongs, and keep the fleet in step with GitLab's release cadence.We work closely with delivery, database, migration, and product teams across GitLab. Feature teams own how their services behave on the platform; we own the underlying infrastructure.We're an all-remote, asynchronous team. We make decisions in GitLab issues, use directly responsible individuals (DRIs) to own technical direction, demo our work weekly, and use AI-assisted workflows every day. How GitLab Supports Full-Time Employees Benefits to support your health, finances, and well-being Flexible Paid Time Off Team Member Resource Groups Equity Compensation & Employee Stock Purchase Plan Growth and Development Fund Parental Leave Please note that we welcome interest from candidates with varying levels of experience; many successful candidates do not meet every single requirement. Additionally, studies have shown that people from underrepresented groups are less likely to apply to a job unless they meet every single qualification. If you're excited about this role, please apply and allow our recruiters to assess your application. Country Hiring Guidelines: GitLab hires new team members in countries around the world. All of our roles are remote, however some roles may carry specific location-based eligibility requirements. Our Talent Acquisition team can help answer any questions about location after starting the recruiting process. Privacy Policy: Please review our Recruitment Privacy Policy. Your privacy is important to us. GitLab is proud to be an equal opportunity workplace and is an affirmative action employer. GitLab’s policies and practices relating to recruitment, employment, career development and advancement, promotion, and retirement are based solely on merit, regardless of race, color, religion, ancestry, sex (including pregnancy, lactation, sexual orientation, gender identity, or gender expression), national origin, age, citizenship, marital status, mental or physical disability, genetic information (including family medical history), discharge status from the military, protected veteran status (which includes disabled veterans, recently separated veterans, active duty wartime or campaign badge veterans, and Armed Forces service medal veterans), or any other basis protected by law. GitLab will not tolerate discrimination or harassment based on any of these characteristics. See also GitLab’s EEO Policy and EEO is the Law . If you have a disability or special need that requires accommodation , please let us know during the recruiting process .

Задачи: — Создавать высокопроизводительные edge-сервисы на Go — Проектировать архитектуру с офлайн-режимом и синхронизацией между облаком и edge — Разрабатывать системы обмена сообщениями с использованием NATS, Kafka или MQTT — Управлять развертываниями в Kubernetes с Helm — Оптимизировать сервисы для работы на edge-оборудовании — Участвовать в архитектурных и код-ревью Требования: — Опыт разработки ПО не менее 7 лет — Уверенные знания Golang — Опыт работы с распределёнными системами и event-driven архитектурой — Знания Kubernetes, Helm, Docker — Опыт работы с системами обмена сообщениями NATS, Kafka или аналогичными — Знание OAuth2 и JWT — Опыт работы с CI/CD Будет плюсом: — Опыт с MQTT — Знание Spectro Cloud Palette — Опыт работы с POS или ресторанными технологиями — Знание GraphQL federation

Location: San Francisco, CA | New York City, NY | Seattle, WA About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. About the role Anthropic’s Inference organization serves Claude to millions of users and enterprise customers, across our own products and the world’s largest cloud platforms, with the speed, reliability, and efficiency that frontier AI demands. The stack that makes this possible is deep and tightly coupled: accelerator kernels, an in-house inference engine that manages the entire token path for both production and research workloads, distributed routing, autoscaling, and capacity management. Every layer affects the others, often in ways that are hard to see in isolation. We build across GPUs, TPUs, and Trainium, and the complexity of building, testing, and shipping inference software grows with every platform we add. We're looking for a Technical Program Manager to drive the programs that scale it. The work spans four closely coupled areas: Scaling and infrastructure. Routing, autoscaling, and capacity management for the serving fleet, and bringing new capacity online. Velocity. The toolchains, development environments, and CI/CD that let inference engineers build, test, and ship across every accelerator platform. Inference engine. The software between the accelerator kernels and the routing layer that serves every request. Performance. Improving throughput, latency, cost, and reliability across the stack, with correctness treated as part of performance. This is not a status-tracking role. You'll own outcomes end to end, often where no single team is accountable for the whole picture. Much of your value comes from crossing boundaries into Research, Safeguards, Security, Compute, Infrastructure, API, and our cloud and silicon partners, and bringing back the requirements and dependencies that no team sees from inside its own space. There is little process to inherit, and we want to keep it that way: you'll build the minimum machinery the work needs and remove it when it stops helping. And because this is Anthropic, you'll have Claude as a collaborator. We expect TPMs on this team to push hard on what AI-assisted program management and fleet operations can look like. Key responsibilities Own the programs that scale Claude’s serving fleet across accelerator and cloud platforms, from early direction through delivery. Drive new capacity online end to end, working across compute, infrastructure, security, networking, and inference teams so one person is accountable for the whole path. Build visibility into supply, demand, and utilization with capacity and finance partners, and drive trade-offs among utilization, cost, latency, and reliability to a clear decision. Lead reliability programs and large migrations without disrupting production traffic or research, and make sure incident follow-ups land in team roadmaps. Drive the programs that make inference engineers faster: define the productivity metrics that matter, find the bottlenecks, and improve how software is built, tested, and released across platforms, in step with Anthropic’s central Infrastructure org. Coordinate roadmaps and priorities across the production, research, and safeguards needs that depend on the same teams. Track performance and efficiency work from opportunity to measured impact in production, with correctness held as a release criterion. Own inference readiness for model launches alongside our launch TPMs. Minimum qualifications 7+ years of experience as a TPM, or in an equivalent engineering or SRE lead role, owning large multi-team infrastructure programs end to end in production distributed systems, ML infrastructure, or cloud platforms. You can speak to the outcomes in detail, including where a program slipped and what you did about it. Technical fluency in large-scale serving infrastructure, including request routing and load balancing, autoscaling, capacity planning, cluster orchestration, deployment and rollout, and observability. You know enough to challenge a design, find the real risk, and add value beyond tracking. A working understanding of how LLM inference uses hardware (prefill and decode, batching, caching, compute versus memory bandwidth versus interconnect), or a track record of getting deep in an unfamiliar technical domain quickly. A track record of building program mechanisms from scratch on ambiguous, fast-moving efforts, and of retiring process that has stopped earning its keep. The ability to drive outcomes across organizations you don't manage, with competing priorities and unclear decision ownership. You read people and rooms well, know when to push and when to listen, and earn the trust of senior engineers and researchers. Strong written communication, including plans, reviews, and executive updates that many teams depend on. Low ego and high ownership. You do whatever the program needs, whether that is writing a script, running an incident bridge, or chasing a quota, and you care more about the outcome than about scope or credit. Care about Anthropic's mission and about serving frontier AI safely and reliably. Preferred qualifications Direct experience with LLM or ML inference serving at scale, such as model servers, batching and scheduling, KV caching, quantization, speculative decoding, or multi-model routing. Experience with accelerator infrastructure (GPU, TPU, or Trainium), including cluster bring-up, hardware qualification, or running one workload across more than one accelerator platform. Experience managing capacity across multiple clouds or regions, including demand forecasting, headroom policy, cost modeling, or unit economics for compute-heavy services. Experience with developer productivity, release engineering, or CI/CD at scale, especially for hardware-dependent workloads, and with using engineering metrics to measurably raise velocity. Experience running performance or efficiency programs, with enough grounding in rooflines, kernels, ML compilers (XLA, Triton, Neuron), numerics, or collective communication to reason about trade-offs with the engineers doing the work. Familiarity with Kubernetes-based orchestration and job scheduling. Experience working with research teams and turning their needs into infrastructure requirements. Practical experience using AI tools in your own workflow, including building automations or agents, and clear ideas about where they help and where they don't. The annual compensation range for this role is listed below. For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role. Annual Salary: $290,000 — $435,000 USD Logistics Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices. Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this. For roles performing work in California: We will consider for employment all qualified applicants, including those with arrest or conviction records or criminal histories, in a manner consistent with the requirements of applicable state and local laws, including the San Francisco Fair Chance Ordinance, the City of Los Angeles’ Fair Chance Initiative for Hiring Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act. We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed.  Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team. Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings. How we're different We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills. The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences. Come work with us! Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process.

Location: San Francisco Workplace: Hybrid ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F https://www.baseten.co/blog/announcing-our-series-f/, led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products. THE ROLE Container runtimes were designed for general-purpose software workloads. AI inference is not a general-purpose workload. Running large models at production scale exposes cracks in every layer of the container stack: runtimes unaware of GPU memory constraints, images that take minutes to pull when a model needs to scale to thousands of replicas, and isolation mechanisms that weren’t designed for the multi-tenant serving environments that production AI requires. The tools the industry has relied on for a decade weren’t built for this, and patching around those limitations at higher layers only goes so far. Baseten owns the entire pipeline, from the moment a developer pushes a model to the moment a request gets a response. That vertical ownership means we can fix these problems at the root. The Runtime Fabric team is doing exactly that: purpose-building the container runtime and storage layers for AI inference workloads, led by some of the world’s top containerd maintainers. As Engineering Manager for Storage Products on the Runtime Fabric team, you will lead the engineers who build and run the storage products behind that stack: the Baseten Delivery Network (BDN), which sits in the cold start path of every model on the platform, the snapshotters and filesystems that expose model weights and container images to a running container, and the storage that model deployment and training need next. The team is advancing the next generation of caching for inference workloads, from the origin tier to the GPU host. You will own reliability for the area as a measured outcome, report to the head of Runtime Fabric, and stay close to the code through design and code review. If you’ve managed systems engineers and have hands-on experience with caching, content-addressable storage, or distributed filesystems, we’d love to talk. EXAMPLE INITIATIVES - How the Baseten Delivery Network (BDN) makes cold starts fast https://www.baseten.co/blog/how-the-baseten-delivery-network-bdn-makes-cold-starts-fast/ - Extending BDN from model weights to container image layers, training checkpoints, and deployment artifacts - Lazy-loading snapshotters and block-level delivery (EROFS, FUSE, ublk) so a container can start before the full image or model has arrived RESPONSIBILITIES Team Leadership and Culture - Hire and grow a team of 5 to 10 systems engineers with storage, caching, and Linux expertise - Run the team’s planning and delivery: scope work against the Runtime Fabric roadmap, set priorities, and ship on a predictable cadence - Provide regular coaching, feedback, and career development support to your direct reports - Own on-call health for the team’s services, including escalation paths and follow-through on incidents Technical Direction - Guide the architecture and evolution of the Baseten Delivery Network: the tiered caching and weight delivery product that makes cold starts 2-3x faster and eliminates thundering herd failures during burst scaling events - Shape storage products tailored to Baseten’s workloads: extend BDN from model weights to container images, training checkpoints, and deployment artifacts, and define the interfaces that model deployment, training, and customers use to reach them - Oversee the on-host side of delivery: lazy-loading snapshotters, EROFS and overlayfs layouts, and block-level delivery (FUSE, ublk) for multi-gigabyte files - Own reliability of the delivery path as a measured outcome: end-to-end instrumentation from snapshotter initialization to first inference request, targets for cold start and cache behavior, tolerance for failing upstream registries and object stores, and safe rollout of changes to a path every customer depends on - Make the delivery path work across heterogeneous clusters and cloud providers, each with its own object store and network - Review designs and code across the area, and take on hands-on work where it unblocks the team - Champion the team’s contributions back to containerd and the snapshotter ecosystem alongside the maintainers on the Runtime Fabric team Cross-Functional Partnership - Act as the point of contact for storage across Baseten, ensuring model deployment, training, and platform teams have the integration support they need - Optimize requirements for the underlying storage platforms with the infrastructure team: object storage, local NVMe and block storage, and network bandwidth per cluster, so that capacity and provider decisions account for what the delivery path needs - Manage the team’s dependencies in both directions: sequence work that model deployment, training, and infrastructure teams block on, and negotiate interfaces and timelines with the teams and upstream projects the storage path depends on - Work with the head of Runtime Fabric and product stakeholders to prioritize storage investments based on customer impact and infrastructure reliability - Communicate team progress, technical trade-offs, and incidents clearly to the team and to leadership REQUIREMENTS - Experience managing a team of engineers in a systems, infrastructure, or storage context, including hiring and performance management - Hands-on background in distributed storage systems, content-addressable storage, or large-scale caching infrastructure - Strong systems programming background in Go, Rust, and/or C/C++, with the ability to engage credibly in code reviews and architectural discussions - Working knowledge of the Linux storage stack: filesystems, the page cache, block devices, and mounts - Understanding of how container images are structured, stored, and delivered at scale - Strong written and verbal communication skills, with the ability to influence without authority across teams NICE TO HAVE - Contributions to containerd/containerd, snapshotter projects (stargz, soci, nydus, overlaybd), distribution/distribution, or closely related open-source projects - Familiarity with lazy-loading snapshotters or peer-to-peer image distribution - Experience with EROFS, FUSE, ublk, or io_uring - Experience building or operating CDN, object storage, or large-scale caching infrastructure - Experience running storage services on Kubernetes BENEFITS - Competitive compensation, including meaningful equity - (U.S. only) 100% coverage of medical, dental, and vision insurance for employee and dependents - Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!) - Paid parental leave - Fertility and family-building stipend through Carrot - (U.S. only) Company-facilitated 401(k) - Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities. Apply now to embark on a rewarding journey in shaping the future of AI! If you are a motivated individual with a passion for machine learning and a desire to be part of a collaborative and forward-thinking team, we would love to hear from you. At Baseten, we are committed to fostering a diverse and inclusive workplace. We provide equal employment opportunities to all employees and applicants without regard to race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status. We are an Equal Opportunity Employer and will consider qualified applicants with criminal histories in a manner consistent with applicable law (by example, the requirements of the San Francisco Fair Chance Ordinance, where applicable).

Требования: — Практический опыт работы в технической поддержке L2, DevOps или системной инженерии веб-систем, связанной с устранением неисправностей в производственных средах, не менее 2 лет. — Доказанный практический опыт в области видеостриминга / OTT / медиа: устранение неисправностей в прямом эфире (RTMP ingest), файловом кодировании/транскодировании и рабочих процессах доставки. — Практическое понимание видеостриминговых протоколов (HLS, DASH), адаптивного потокового вещания (ABR), кодеков, контейнеров и распространённых паттернов ошибок воспроизведения. — Практический опыт диагностики браузера с использованием Chrome DevTools: проверка консоли, сетевых трасс, заголовков CORS, захвата HAR, анализ видеосегментов/манифестов и проблем с буферизацией. — Глубокое понимание концепций REST API, HTTP-методов/заголовков/кодов состояния и практический опыт отладки API (Postman, curl). — Отличные навыки работы с командной строкой Linux. — Практический опыт анализа журналов службы и проверки состояния pod/service в Docker и Kubernetes (kubectl). — Готовность к работе в нерабочее время (покрытие вызовов): с понедельника по пятницу с 00:00 до 05:30 CET, в субботу и воскресенье круглосуточно. — Уровень английского языка – Upper-Intermediate и выше. Задачи: — Обеспечение L2 технической поддержки в нерабочее время для корпоративных видеопотоков и рабочих процессов кодирования. — Управление жизненным циклом инцидентов от начала до конца: триаж, регистрация тикетов, глубокий анализ первопричин (RCA), внедрение обходных решений и разрешение проблем в рамках строгих SLA-целей. — Устранение неисправностей в интеграциях REST API: проверка конечных точек, аутентификации/токенах, заголовках, ошибках CORS-префлайтов и полезной нагрузки; воспроизведение повторяемых вызовов через Postman/curl. — Диагностика проблем веб-плеера (JS/TS) с использованием Chrome DevTools: проверка вкладок Console и Network, анализ буферизации, проверка наличия манифеста и сегментов (HLS, DASH). — Проверка конвейеров потокового вещания и кодирования: проверка состояния RTMP-ввода, исправность кодировщика, транскодирование конвейеров и адаптивная доставка с переменной скоростью передачи данных. — Чтение и анализ журналов контейнеров и сервисов через Docker и Kubernetes (kubectl logs, статусы подов/сервисов, события) в многооблачных средах (в основном GCP). — Исследование базовых проблем с сетью, прокси и шлюзами (TLS-сертификаты, HTTP/HTTPS, конфигурации Nginx/HAProxy). — Документирование хода инцидента и общение с клиентами в Zendesk/Jira, предоставление четких обновлений. — Эскалация сложных проблем до L3-инженеров с хорошо структурированным контекстом: журналы, шаги воспроизведения, рабочие гипотезы и собранные артефакты в хранилище объектов (S3/GCS). — Поддержание чистоты тикетов и соблюдение процедур передачи смен между дежурствами. Условия: — Работа в компании Andersen Kazakhstan Ltd. — Гибкий график. — Удаленная работа. — Частичная занятость. — Опыт работы не менее 2 лет. — Уровень английского Upper-Intermediate и выше. — Готовность к работе в нерабочее время (покрытие вызовов) по расписанию: с понедельника по пятницу с 00:00 до 05:30 CET, в выходные круглосуточно. — Персональные данные защищены в соответствии с правилами GDPR. — Возможность профессионального, финансового и карьерного роста. — Доступ к корпоративному обучающему порталу. — Компенсация за сертификацию (AWS, PMP и т.д.). — Частная медицинская страховка и компенсация за спортивные мероприятия. — Реферальная программа. — Возможность сменить проект и развить экспертизу. — Работа с лидерами в различных отраслях. — Возможность дополнительного заработка до 1000 EUR в годовом бонусе.