Задачи:
— самостоятельно вести продуктовые задачи в роли системного аналитика
— собирать и уточнять требования с заказчиком, анализировать BRD
— проектировать целевую архитектуру сервисов и интеграций
— участвовать в проектировании решений с использованием AI-агентов
— описывать взаимодействие AI-компонентов и интеграции с внешними системами
— готовить технические задания и детальные спецификации для разработки
— моделировать процессы в BPMN и UML (activity, sequence)
— участвовать в проработке архитектурных решений и интеграционном тестировании
— взаимодействовать с бизнесом, разработчиками и другими участниками проекта
Требования:
— опыт работы системным аналитиком от 3 лет
— опыт продуктовой разработки и самостоятельного ведения задач
— практический опыт работы с ИИ-агентами, LLM и RAG
— понимание MCP и LangFuse
— уверенное знание BPMN, UML activity/sequence
— опыт проектирования REST-интеграций, понимание SOAP, XSD
— понимание синхронного и асинхронного взаимодействия
— уверенный SQL — написание сложных запросов
— понимание ER-моделей и принципов проектирования баз данных
— понимание основ информационной безопасности: идентификация, аутентификация, авторизация, шифрование и хэширование
— PlantUML, ArchiMate
— опыт работы с Kafka, gRPC
— опыт работы в финтехе
— практическое использование AI-инструментов в ежедневной работе
Условия:
— полная занятость
— график 5/2
— удалённый формат работы
Контакт для отклика: job@selecty.ru
Задачи:
— Разрабатывать и совершенствовать AI-инструменты, агенты и рабочие процессы, повышающие эффективность и качество работы QA-команды.
— Определять повторяющиеся или значимые QA-активности и превращать их в масштабируемые AI-решения.
— Создавать интеграции между AI-возможностями и системами тестирования, инженерии и внутренними системами.
— Определять технические стандарты и лучшие практики для AI-решений в QA, включая промпты, контекст, инструменты, рабочие процессы агентов и процессы с участием человека.
— Разрабатывать механизмы оценки AI-выходных данных, измерения качества и обнаружения регрессий.
— Контролировать и улучшать надежность, производительность и стоимость AI-решений.
— Быть техническим центром компетенций по AI в QA-команде, способствовать внедрению, обмену знаниями и экспериментам.
— Тесно сотрудничать с QA-инженерами и инженерными командами для превращения реальных задач в практические решения.
Требования:
— Опыт работы 5+ лет в области Software Quality Engineering, Test Automation или Software Engineering.
— Опыт работы с фреймворками автоматизации тестирования, такими как Playwright, Cypress или аналогичными.
— Навыки программирования на JavaScript/TypeScript или Python.
— Практический опыт создания AI-инструментов, приложений, рабочих процессов или агентов с использованием LLM.
— Понимание агентных рабочих процессов, prompt и context engineering, tool calling, MCP и интеграций API.
— Опыт превращения экспериментальных решений в надежные и поддерживаемые инженерные продукты.
— Знания основ QA, включая дизайн тестов, регрессионное и исследовательское тестирование.
— Опыт работы с API, базами данных и распределенными системами.
— Опыт работы с CI/CD системами, такими как GitHub Actions, Jenkins или аналогичными.
— Сильные навыки решения проблем и способность самостоятельно вести технические инициативы.
Будет плюсом:
— Опыт оценки выходных данных LLM или агентов и измерения качества AI-решений.
— Опыт создания внутренних платформ для разработчиков, инженеров или QA.
— Опыт работы с системами наблюдаемости и распределенными системами.
— Опыт интеграции AI с инструментами, такими как GitHub, Jira, Confluence или CI/CD платформами.
— Опыт работы с Kubernetes или облачной инфраструктурой.
— Опыт в AdTech или программной рекламе.
Условия:
— Поддержка от HR-команды.
— 20 дней оплачиваемого отпуска.
— Оплата членства в Multisport.
— Медицинская страховка.
— Конкурентная компенсация, отражающая вклад и усилия сотрудника.
УдалённоseniorГеография найма не уточнена, офис: Poland
Задачи:
— Проектировать и развивать LLM/AI-системы и AI-агентов;
— Строить многошаговые agentic workflows: routing, tool calling, state management;
— Работать с Prompt Engineering и Context Engineering;
— Управлять контекстом, памятью и состоянием диалога;
— Реализовывать structured output и function/tool calling;
— Строить RAG-пайплайны: chunking, embeddings, retrieval, reranking;
— Интегрировать LLM с API, базами данных и внутренними сервисами;
— Разрабатывать backend-сервисы на Go и AI-компоненты на Python;
— Исследовать новые модели и подходы, быстро проверять гипотезы;
— Выбирать модели с учетом качества, latency и стоимости;
— Строить систему оценки качества: evals, regression tests, golden datasets, LLM-as-a-judge;
— Анализировать логи и traces, улучшать качество и стабильность агентов;
— Реализовывать retries, fallbacks, timeouts и обработку ошибок;
— Доводить решения от прототипа до стабильного production.
Требования:
Go:
— production-сервисы;
— REST/gRPC API;
— concurrency;
— работа с БД;
— микросервисная архитектура.
Python:
— AI-сервисы и backend;
— async;
— API;
— обработка данных;
— быстрое прототипирование.
Также важно:
— Практический опыт разработки production-приложений с LLM;
— Понимание архитектуры современных AI-систем: prompt → context → tools → agent → state → evaluation;
— Опыт Prompt Engineering: system prompts, few-shot, prompt chaining, structured output;
— Опыт Context Engineering: memory, summarization, динамическая сборка контекста;
— Опыт создания AI-агентов и agentic workflows;
— Работа с LLM API и понимание особенностей разных моделей;
— Понимание RAG: embeddings, vector search, retrieval, reranking, hybrid search;
— Понимание evals, regression testing и анализа production-логов;
— Опыт с PostgreSQL, MongoDB, Redis, Docker, Git, CI/CD;
— Понимание production-подходов: observability, scalability, latency, retries, fallbacks и контроль стоимости.
Будет плюсом:
— Multi-agent системы;
— LangGraph;
— MCP;
— Langfuse / LangSmith;
— Elasticsearch / OpenSearch;
— Open-source LLM: Qwen, Llama, DeepSeek и др.;
— vLLM / Ollama;
— Kafka / RabbitMQ;
— Kubernetes;
— Оптимизация token usage, latency и стоимости LLM;
— Guardrails и защита от prompt injection;
— Highload-системы.
Важно:
Ищем инженера, который воспринимает LLM не как простой API, а как компонент большой production-системы. Важно уметь проектировать всю логику вокруг модели: какие данные передать в контекст, какого агента или инструмент вызвать, как проверить результат, обработать ошибку и определить следующий шаг. Ищем software engineer с сильной AI/LLM-экспертизой, который умеет не только написать хороший промпт, но и довести всю систему до стабильного production-решения.
Location: United States, Aliso Viejo, CA
Why Sony Interactive Entertainment?
Sony Interactive Entertainment isn’t just the Best Place to Play — it’s also the Best Place to Work. Sony Interactive Entertainment (SIE) is the company behind the PlayStation brand. As a subsidiary of Sony Group Corporation, we’re part of a proud legacy of innovation and excellence. SIE is a dynamic technology company, delivering cutting-edge hardware and network services to more than 100 million people and an entertainment leader, home to some of the most beloved and recognizable intellectual properties (IP) in the world. Our role at SIE is to create and nurture the experiences under the PlayStation brand, a name synonymous with entertainment excellence and creativity.
Senior Software Engineer - AI & Agentic Architecture
This is a senior individual-contributor role combining deep hands-on engineering with multiple agentic frameworks & SDKs, harnesses, MCP, and APIs, technical leadership, and close collaboration with engineering, security, and product teams. You'll design and ship agentic systems, developer tooling, and reusable platform capabilities that improve productivity across SIE.
What you'll do:
Agentic & AI Engineering
Design, build, and operate production-quality agentic applications using agentic SDKs/harnesses — including multi-agent orchestration, subagent delegation, tool integration, and lifecycle hooks.
Design Model Context Protocol (MCP) tool and resource interfaces that give coding agents/harnesses safe, reliable access to backend systems and enterprise data.
Engineer prompts for reliable structured output (JSON schemas, few-shot examples, validation/retry loops) and build evaluation frameworks to measure and improve output quality.
Manage context effectively across long documents, multi-turn conversations, and multi-agent handoffs; design escalation and human-in-the-loop patterns for production reliability.
Developer Productivity
Configure and extend Codex/Claude Code for team-wide use:
AGENTS.md/CLAUDE.md
hierarchies, custom slash commands, Agent Skills, path-specific rules, and plan mode.
Integrate agentic development into CI/CD pipelines for automated code review, test generation, and PR feedback, tuned to minimize false positives and duplicate findings.
Build and maintain MCP server integrations (project- and user-scoped) that extend agent-native development capabilities across engineering workflows.
Identify high-value opportunities for AI-assisted development and design reusable capabilities that multiple teams can adopt, not just one-off solutions.
Discovery, Prototyping & Production Delivery
Partner directly with engineering teams to understand workflows, pain points, and opportunities through hands-on discovery.
Rapidly prototype and validate new AI capabilities with real users, then take successful prototypes into secure, observable, maintainable production systems.
Own the full lifecycle: implementation, testing, deployment, monitoring, and iteration.
Technical Leadership
Provide hands-on technical leadership through architecture discussions, code reviews, and troubleshooting of agentic systems.
Mentor engineers on agentic design patterns, prompt engineering, and agent-native development practices.
Communicate tradeoffs, risks, and results clearly to both technical and non-technical stakeholders.
Contribute to engineering standards, reusable patterns, and documentation that help other teams build effectively with agentic development tools.
Requirements
6+ years of professional software engineering experience, including significant hands-on work building and operating AI/LLM-powered or agentic applications.
Strong programming skills (Java, Python, Go, Rust, or C++) and solid engineering fundamentals — API design, testing, debugging, code review, maintainable code.
Practical, production-grade experience with agentic SDKs/harnesses, MCP, and LLMs — tool use, orchestration, RAG, context management, structured output, and evaluation.
Experience designing MCP tool/resource interfaces and reasoning about tool selection, error handling, and reliability in multi-agent systems.
Demonstrated experience integrating AI into CI/CD and developer workflows.
Ability to work in ambiguous problem spaces, evaluate tradeoffs, and make pragmatic engineering decisions.
Strong written and verbal communication skills, with experience mentoring and leading through influence.
Bachelor’s degree or equivalent.
Preferred Qualifications
Demonstrated expertise across agentic architecture, MCP integration, Codex/Claude Code configuration, prompt engineering, and context management.
Experience building multi-agent research or customer support systems, or structured data extraction pipelines.
Experience with AWS, Docker, Kubernetes, Terraform, and GitOps in support of AI/agentic infrastructure.
Familiarity with vector databases, embeddings, and AI evaluation frameworks.
Contributions to open-source projects involving AI, agentic systems, or developer tooling.
Strong systems thinking — understands how models, agents, tools, context, APIs, data, and infrastructure fit together as production systems, and can reason about dependencies and tradeoffs across the stack.
A track record of adapting quickly to new AI tools, models, and frameworks as the space evolves.
At SIE, we consider several factors when setting each role’s base pay range, including the competitive benchmarking data for the market and geographic location.
Please note that the base pay range may vary in line with our hybrid working policy and individual base pay will be determined based on job-related factors which may include knowledge, skills, experience, and location.
In addition, this role
is eligible
for SIE’s top-tier benefits package that includes medical, dental, vision, matching 401(k), paid time off, wellness program and coveted employee discounts for Sony products.
This role also may be eligible for a bonus package.
Click
here
to learn more.
The estimated base pay range for this role is listed below.
$177,300
—
$265,900 USD
Please note, Sony Interactive Entertainment conducts background checks at the offer stage for all new employees (which may include criminal background checks for some roles) and will need to process personal information to support these checks.
Please refer to our Candidate Privacy Notice (where applicable) for more information about what personal information we collect, how we use it, who we share it with, and your data protection rights.
Equal Opportunity Statement:
Sony is an Equal Opportunity Employer. All persons will receive consideration for employment without regard to gender (including gender identity, gender expression and gender reassignment), race (including colour, nationality, ethnic or national origin), religion or belief, marital or civil partnership status, disability, age, sexual orientation, pregnancy, maternity or parental status, trade union membership or membership in any other legally protected category.
We strive to create an inclusive environment, empower employees and embrace diversity. We encourage everyone to respond.
Sony Interactive Entertainment is a Fair Chance employer and qualified applicants with arrest and conviction records will be considered for employment.
Задачи:
— Разработка AI-агентов, которые выполняют рабочие процессы, а не только чат-интерфейсы.
— Работа с агентами, которые подключаются к API и внутренним системам, используют инструменты, извлекают контекст, принимают решения на нескольких шагах и восстанавливаются при сбоях.
Требования:
— Опыт разработки на Python и бекенд инженерия.
— Опыт работы с LLM API и агентными системами в продакшене.
— Знание LangGraph, LangChain, LlamaIndex или аналогичных технологий.
— Опыт работы с вызовом функций/инструментов и структурированными выводами.
— Знание RAG, embeddings, векторного поиска и управления контекстом.
— Опыт работы с состоянием агента, памятью, маршрутизацией, повторными попытками и логикой резервного копирования.
— Интеграция API и событийно-ориентированные рабочие процессы.
— Оценка, трассировка и отладка LLM.
— Опыт работы с Docker, Kubernetes, CI/CD и AWS.
— Приветствуется опыт мультиагентной оркестрации, MCP, workflows с участием человека и мониторингом агентов в продакшене.
Условия:
— Удалённая работа.
— Полная занятость или контракт.
Задачи:
— Разработка AI-агентов, которые выполняют рабочие процессы, а не только чат-интерфейсы.
— Работа с агентами, которые подключаются к API и внутренним системам, используют инструменты, извлекают контекст, принимают решения на нескольких шагах и восстанавливаются при сбоях.
Требования:
— Опыт разработки на Python и бекенд инженерия.
— Опыт работы с LLM API и агентными системами в продакшене.
— Знание LangGraph, LangChain, LlamaIndex или аналогичных технологий.
— Опыт работы с вызовом функций/инструментов и структурированными выводами.
— Знание RAG, embeddings, векторного поиска и управления контекстом.
— Опыт работы с состоянием агента, памятью, маршрутизацией, повторными попытками и логикой резервного копирования.
— Интеграция API и событийно-ориентированные рабочие процессы.
— Оценка, трассировка и отладка LLM.
— Опыт работы с Docker, Kubernetes, CI/CD и AWS.
— Приветствуется опыт мультиагентной оркестрации, MCP, workflows с участием человека и мониторингом агентов в продакшене.
Условия:
— Удалённая работа.
— Полная занятость или контракт.
Location: San Francisco
Workplace: Hybrid
About WorkOS 🚀
WorkOS builds modern developer tools and APIs that make it easy for companies to become Enterprise Ready. Our platform powers authentication, identity, authorization, and other critical infrastructure that developers need to securely scale their products to large organizations.
We recently raised a $100M Series C, valuing the company at $2B, led by Meritech and Sapphire with participation from Greenoaks, Craft, Abstract, and Audacious. WorkOS powers enterprise features for many of the fastest-growing AI companies, including OpenAI, Cursor, and Perplexity, Sierra, and Plaid.
As AI reshapes software, WorkOS is at the frontier of Human and Agent Authentication, Identity, and Access Control helping companies answer a new critical question: who are your agents, and what are they allowed to do? Our fast-growing customer base includes hundreds of modern software companies building the next generation of enterprise-ready products.
ABOUT THE ROLE
We’re hiring an experienced Engineering Manager to lead Dashboard, the team helping customers get more value from the WorkOS suite and helping WorkOS grow as a business. We’re looking for a leader who is excited to manage engineers, but approaches the role as a startup founding member would.
You’ll lead engineers working across customer onboarding and growth, billing and monetization, and AI assistance in the WorkOS dashboard. The team’s work connects the customer journey from signup and integration through production and expansion. You’ll partner closely with design, go-to-market, finance, and other engineering teams to make that journey simpler and more effective.
This role offers meaningful autonomy to shape what we build and why. It’s a great fit for a strong product thinker who enjoys working closely with product managers and taking the lead on product decisions when the opportunity calls for it. You’ll have room to identify customer problems, propose new directions, and carry ideas from discovery through launch, with ownership of the outcomes. If you’re excited by the chance to combine engineering leadership with product judgment, there’s a lot to build here.
You’ll also drive technical strategy, empower your team to execute on projects with a direct impact on customer success and the business, and play a pivotal role in scaling the team and recruiting exceptional engineers.
WHAT YOUR TEAM WILL BUILD
- Growth and onboarding: help developers move from signing up to integrating and running WorkOS in production. Improve onboarding and next steps, and work with go-to-market teams on timely outreach informed by product signals.
- Billing and monetization: build annual-credit capabilities, make billing more reliable and automated, and give customers clearer pricing, usage, and credit information in the dashboard.
- AI assistance for developers: bring the Dashboard Agent, WorkOS MCP server, Ask WorkOS, and Support Bot into a coordinated experience, with shared retrieval, evaluations, and quality standards. Help developers get useful, consistent answers and make progress with WorkOS.
RESPONSIBILITIES
- Build and lead a high-velocity team that ships product fast and with polish across growth, monetization, and developer assistance.
- Be deeply technical and hands-on: read the PRs, write prototypes, and work with technical leads on architecture and project scope.
- Shape the roadmap in close partnership with product managers, design, go-to-market, finance, and engineering. Bring your own product perspective, identify opportunities, and drive product decisions directly where needed—from defining the problem and choosing an approach to measuring the outcome.
- Help the team improve the customer journey from signup to production and expansion, using product signals and customer feedback to choose what to build next.
- Balance rapid product iteration with the reliability and correctness customers need from billing and the quality they expect from AI assistance.
- Push for clarity, focus, and high energy in every sprint. Drive urgency without burning people out.
- Spend time with customers and engineers alike—digging into pain points, testing assumptions, and improving the craft.
- Coach, mentor, and grow a team of curious, driven engineers through direct feedback, clear goals, and meaningful ownership.
- Partner with recruiting to attract, hire, and retain exceptional engineering talent.
QUALIFICATIONS
- Track record of having successfully led product-focused engineering teams in high-performing organizations that shipped real impact.
- You've written code at a high level, and you still love to get your hands dirty. You view leadership as an amplifier, not a step back.
- Bias for action and scrappiness: You don’t over-optimize for process. You optimize for velocity, customer value, and learning.
- You deeply care about the developer experience. You think about UX, APIs, performance, edge cases, and joy.
- You ask "why" obsessively, and you push yourself (and your team) to learn constantly.
- You build trust, give direct feedback, and create space for engineers to thrive.
- You have experience partnering with internal recruiting teams to drive effective and fair hiring processes. You realize that recruiting is a large and important part of your role, and have a track record of recruiting, hiring, and mentoring top engineering talent.
- You’re a strong product thinker who connects customer needs, technical possibilities, and business outcomes. You collaborate well with product managers and are comfortable driving product decisions yourself, using customer insight and evidence to make tradeoffs and build alignment.
Experience with onboarding and growth, billing systems, or customer-facing AI products is especially relevant. You do not need prior experience in all three areas.
Benefits and Perks (US Only) 💖
At WorkOS, we offer resources that emphasize personal and familial well-being. We offer healthcare coverage for you and your family, including medical, dental, and vision. We offer parental leave, paid-time off and fully remote working arrangements.
- 401k matching
- Competitive Equity
- Healthcare, dental and vision coverage
- FSA, ST/LT Disability, Voluntary Life
- Carrot fertility benefits
- 20 days paid vacation + 10 holidays + unlimited sick leave
- 12 weeks fully paid parental leave
- Fitness: Monthly stipend for gyms, yoga classes, race registrations or whatever keeps you active
- Wellness: Monthly stipend for a massage, meditations class, therapy, or activities that enhance your well-being
- Commuter benefits for hybrid employees in SF/NYC
- Unlimited token usage!
Please inquire directly with our recruiting team for benefits available to those working outside the US.
Equal Opportunity Employer
WorkOS is an equal opportunity employer, committed to diversity and inclusiveness. We will consider all qualified applicants without regard to race, color, nationality, gender, gender identity or expression, sexual orientation, religion, disability or age.
We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.
Задачи:
— Разработка AI-агентов, которые выполняют рабочие процессы, а не только чат-интерфейсы.
— Работа с агентами, которые подключаются к API и внутренним системам, используют инструменты, извлекают контекст, принимают решения на нескольких шагах и восстанавливаются при сбоях.
Требования:
— Опыт разработки на Python и бекенд инженерия.
— Опыт работы с LLM API и агентными системами в продакшене.
— Знание LangGraph, LangChain, LlamaIndex или аналогичных технологий.
— Опыт работы с вызовом функций/инструментов и структурированными выводами.
— Знание RAG, embeddings, векторного поиска и управления контекстом.
— Опыт работы с состоянием агента, памятью, маршрутизацией, повторными попытками и логикой резервного копирования.
— Интеграция API и событийно-ориентированные рабочие процессы.
— Оценка, трассировка и отладка LLM.
— Опыт работы с Docker, Kubernetes, CI/CD и AWS.
— Приветствуется опыт мультиагентной оркестрации, MCP, workflows с участием человека и мониторингом агентов в продакшене.
Условия:
— Удалённая работа.
— Полная занятость или контракт.
Location: Bulgaria; Croatia; Cyprus; Estonia; Finland; Greece; Hungary; Ireland; Latvia; Lithuania; Malta; Moldova; Montenegro; North Macedonia; Poland; Romania; Slovakia; Slovenia; Sweden; Ukraine
Why Kimchi?
Kimchi is the AI platform inside CAST AI. We started by helping companies run LLMs on their own Kubernetes clusters and now we're providing a managed variant of those same capabilities.
Our Infrastructure today
Multi-model inference (MiniMax, Kimi, GLM-5, Nemotron, DeepSeek) with intelligent routing, an OpenAI-compatible API and deployment ranging from our GPUs to your own VPC. The inference layer is the foundation and the API is what sits in front of it as the primary channel for broadly and reliably distributing our AI services and powers our own Kimchi harness.
As a Senior Software Engineer, you will have the opportunity to work on different key features of our product. All of these are high-agency roles across multiple parts of the tech stack that minimize process friction that would otherwise prevent you from shipping.
In every team you will own features end-to-end: design, implementation, testing, production rollout. Most projects ship in 1-4 weeks. You'll work directly with product and other engineering teams on problems that don't have textbook solutions.
We are currently hiring
Senior Software Engineers
for the
Harness team
:
OpenAI and Anthropic ship models. They also ship one harness each – the scaffolding that turns a raw model into something that can plan, execute, recover, and complete work. We ship a different kind of harness: one built for cost-conscious, long-horizon autonomy, running on inference infrastructure we control end-to-end.
A decent model with a great harness beats a great model with a bad harness. We've watched this play out. The gap between what today's models can do and what you see them doing is largely a harness gap – and that gap is where we operate.
Responsibilities:
Architect planner/executor/evaluator pipelines – planning with a reasoning model, execution with a fast one, evaluation with a third. No self-verification.
Manage agent memory and context – state persistence across sessions, context compaction, tool-call offloading
Own the harness surface - TUI, MCP integrations, telemetry.
Work directly with users - including our own colleagues - to identify, understand and fix pain points
Requirements
Production experience with Go or Typescript is strongly preferred; candidates without either should demonstrate strong systems programming skills in a comparable language.
Strong debugging, optimization, and performance-tuning skills – including query profiling, index design, and database performance tuning beyond ORM usage.
Hands-on experience with cloud platforms (AWS, GCP, or Azure) and Kubernetes is a strong plus
Observability tooling (Prometheus, Grafana, OpenTelemetry), CI/CD and DevOps practices experience.
Startup mindset: adaptable, proactive, and comfortable with ambiguity.
Strong English skills, both verbal and written.
You've personally driven a complex project end-to-end.
(Harness) Experience on working with harnesses and creating your own AI workflows is a strong plus
What’s in it for you?
Competitive salary (€6,500 - €9,000 gross, 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:
— Разработка AI-агентов, которые выполняют рабочие процессы, а не только чат-интерфейсы.
— Работа с агентами, которые подключаются к API и внутренним системам, используют инструменты, извлекают контекст, принимают решения на нескольких шагах и восстанавливаются при сбоях.
Требования:
— Опыт разработки на Python и бекенд инженерия.
— Опыт работы с LLM API и агентными системами в продакшене.
— Знание LangGraph, LangChain, LlamaIndex или аналогичных технологий.
— Опыт работы с вызовом функций/инструментов и структурированными выводами.
— Знание RAG, embeddings, векторного поиска и управления контекстом.
— Опыт работы с состоянием агента, памятью, маршрутизацией, повторными попытками и логикой резервного копирования.
— Интеграция API и событийно-ориентированные рабочие процессы.
— Оценка, трассировка и отладка LLM.
— Опыт работы с Docker, Kubernetes, CI/CD и AWS.
— Приветствуется опыт мультиагентной оркестрации, MCP, workflows с участием человека и мониторингом агентов в продакшене.
Условия:
— Удалённая работа.
— Полная занятость или контракт.
Задачи:
— Разработка AI агентов, которые выполняют рабочие процессы, а не только чат-интерфейсы.
— Работа с агентами, которые подключаются к API и внутренним системам, используют инструменты, извлекают контекст, принимают решения на нескольких шагах и восстанавливаются при ошибках.
Требования:
— Опыт разработки на Python и бекенд инженерия.
— Опыт работы с LLM API и агентными системами в продакшене.
— Знание LangGraph, LangChain, LlamaIndex или аналогичных технологий.
— Опыт работы с вызовом функций/инструментов и структурированными выводами.
— Знание RAG, embeddings, векторного поиска и управления контекстом.
— Опыт работы с состоянием агента, памятью, маршрутизацией, повторными попытками и логикой резервного копирования.
— Интеграция с API и событийно-ориентированные рабочие процессы.
— Оценка, трассировка и отладка LLM.
— Опыт работы с Docker, Kubernetes, CI/CD и AWS.
— Преимуществом является опыт с мультиагентной оркестрацией, MCP, human-in-the-loop рабочими процессами или мониторингом агентов в продакшене.
Условия:
— Удалённая работа.
— Полная занятость или контракт.
Это практическая инженерная роль с ответственностью за дизайн агента, реализацию, оценку, деплой и надёжность в продакшене.
Workplace: none
About Utorg
Founded in 2019, Utorg builds the infrastructure for stablecoin payments: on- and off-ramps, self-custodial wallets, and crypto cards. Over 2 million users across 130+ countries already buy, hold, and spend crypto through our app. On the B2B side, the same rails power 2,100+ platforms, with $2.4B+ moved to date.
Fully MiCA-authorized across the EEA. PCI DSS Level 2 certified, backed by Dragonfly, TA Ventures, and Hypra.
Location: Remote
Tech stack
Frontend: React 18/19, TypeScript, Vite, TanStack Query / Router / Table, Zustand, MUI, Tailwind + shadcn/ui, Next.js, i18next, Sentry
Testing: Playwright, Vitest, Testing Library, MSW
Backend: Java 17 + Spring Boot 3, Kotlin + Spring Boot 4 (new services), Node.js/TypeScript services, PostgreSQL, Redis, NATS, Temporal
Infrastructure: Docker, Kubernetes (GKE), FluxCD, GitHub Actions, Cloudflare
Web3: viem, ethers
AI: Claude Code, MCP, custom skills and plugins, AI code review in CI
The role
We are looking for a senior engineer who builds product features end-to-end — mostly on the frontend, with the confidence to change the backend when the feature needs it — and who already works agent-first. Our team plans, writes, tests, and reviews code with AI agents. You will own the frontend of our payment products and help turn good AI habits into shared team workflows.
The split is roughly 70% frontend / 30% backend.
What you will work on
Crypto on/off-ramp widget — an embeddable buy/sell flow with KYC, card payments with 3-D Secure, alternative payment methods, and a customer account area—one codebase, built for multiple white-label brands.
Merchant checkout — hosted payment pages, from a simple one-step checkout to a full multi-step flow with KYC and compliance screens.
Back-office admin apps — internal tools that operations, compliance, and support use every day. A legacy admin is being replaced by a new one built on a modern stack.
Backend changes — API endpoints and business logic in our Java/Spring Boot services, so a feature doesn't stop at the API boundary.
Responsibilities
Own features from ticket to production: UI, API contract, backend change, tests, release, and monitoring.
Make frontend architecture decisions and drive ongoing migrations (legacy admin → new admin, older UI libraries → modern stack, stricter type checks).
Build and improve AI-driven development workflows: project context files, shared skills and commands, automated PR review in CI, agent-driven end-to-end and visual checks.
Review code — both teammates' and agents' — and keep the quality bar high.
Work with product, design (Figma), QA, and backend engineers in a weekly release cycle.
Must have
5+ years of commercial frontend development, 3+ years with React + TypeScript in production.
Solid modern React: server-state management
(TanStack Query or similar), client state (Zustand/Redux), forms, routing, performance. Comfortable with large legacy codebases, not just greenfield projects.
Production backend experience in at least one language.
Java or Kotlin with Spring is a plus; Node.js/TypeScript, Go, or others are fine. You can design a REST API, work with PostgreSQL (schema, indexes, migrations), and ship changes in our Java services.
Agentic development is your daily way of working — with Claude Code, Codex, or a similar agent, not just autocomplete. Specifically:
you keep project context files (
CLAUDE.md
/
AGENTS.md
) and write your own skills, commands, or subagents;
you connect agents to real tools through MCP (issue tracker, GitHub, Figma, databases, browser);
you work in a plan → implement → verify loop, where the agent proves its work with tests, type checks, and browser automation;
you run agents in parallel and headless (for example, an AI review bot in CI);
you review agent output critically and know the failure modes: invented APIs, silent scope creep, "fixing" a test instead of the code, leaked secrets, prompt injection;
you keep up with how agentic tools change (new features, models, practices) and bring what works into your workflow
.
Testing: Playwright for end-to-end, Vitest/Jest for unit and integration tests.
Security-minded: real money, personal data, auth tokens, iframes, and cross-origin messaging.
Fluent Russian (the team's working language). English good enough to read and write technical texts: tasks, pull requests, and docs are in English.
Nice to have
Payments/fintech: card flows and 3-D Secure, alternative payment methods, KYC SDKs (e.g., SumSub), fraud prevention, open banking.
Web3 on the frontend: viem / ethers, wallet connection, EIP-712 signing.
Multi-brand (white-label) products, theming and design tokens.
OpenAPI-generated clients (Orval), TanStack Router / Table.
Kotlin, Spring Boot, NATS, Temporal.
Docker, Kubernetes, GitHub Actions, GitOps (FluxCD), Cloudflare Workers.
How we work with AI
Every main repository has AI context files and repo-specific skills.
An internal plugin marketplace ships team-wide skills (code review, release flow, back-office operations).
AI code review runs on pull requests in CI. It advises, and humans decide.
Custom MCP servers provide agents with secure access to internal systems.
The company pays for AI tooling.
What we offer
Fully remote work in an international team.
A team where AI-first engineering is the norm, not an experiment.
Real influence on architecture and on how the team works.
A product at real scale: millions of users and thousands of partner platforms.
Competitive salary based on individual performance review.
Transparent feedback culture that values ownership and visible impact.
Recruitment process
Apply with your CV.
Application review.
HR interview with a short technical screen.
Technical interview.
Final interview with the CTO.
Offer.
Задачи:
— писать интеграции AI-агентов с корпоративными системами;
— допиливать внутренние сервисы: авторизация, логирование, личные кабинеты, дашборды;
— собирать лендинги и продуктовые страницы из готовых блоков под брендбук;
— делать UI поверх AI-сервисов: дашборды, плагины для мессенджера, обучающие интерфейсы;
— поднимать сервисы в инфраструктуре компании, привязывать домены, чинить мониторинг;
— выполнять микс задач под сильные стороны и интересы, слабые прокачивать с менторами.
Требования:
— знакомство с LLM-харнесом (Claude Code / Codex / VS Code + Claude Code extension), понимание контекста, скиллов, sub-agents, MCP;
— базовые навыки чтения и изменения чужого кода на Python / JS / TS;
— умение работать с Linux, Docker, Git на уровне уверенного пользователя терминала;
— самостоятельность в декомпозиции и продвижении задач, ментор для архитектурных вопросов и ревью;
— английский на уровне чтения документации.
Будет плюсом:
— знание Next.js / React / TypeScript, Tailwind, shadcn/ui;
— опыт написания сервисов на Python / Node.js;
— опыт работы с n8n, DeepResearch, деплоем и CI/CD;
— умение работать с Figma, базовое SEO.
Условия:
— возможность начать карьеру в AI-разработке на старте рынка с быстрорастущим направлением;
— работа с реальными задачами и AI-инструментами для автоматизации и ускорения процессов;
— опыт работы в R&D-команде с экспериментами и внедрением AI-решений;
— доступ к ведущим AI-инструментам и подпискам за счёт компании;
— обучение через практику, внутреннюю экспертизу и специализированные курсы.
Задачи:
— Разработка AI агентов, которые выполняют рабочие процессы, а не только чат-интерфейсы.
— Работа с агентами, которые подключаются к API и внутренним системам, используют инструменты, извлекают контекст, принимают решения на нескольких шагах и восстанавливаются при ошибках.
Требования:
— Опыт разработки на Python и бекенд инженерия.
— Опыт работы с LLM API и агентными системами в продакшене.
— Знание LangGraph, LangChain, LlamaIndex или аналогичных технологий.
— Опыт работы с вызовом функций/инструментов и структурированными выводами.
— Знание RAG, embeddings, векторного поиска и управления контекстом.
— Опыт работы с состоянием агента, памятью, маршрутизацией, повторными попытками и логикой резервного копирования.
— Интеграция с API и событийно-ориентированные рабочие процессы.
— Оценка, трассировка и отладка LLM.
— Опыт работы с Docker, Kubernetes, CI/CD и AWS.
— Преимуществом является опыт с мультиагентной оркестрацией, MCP, human-in-the-loop рабочими процессами или мониторингом агентов в продакшене.
Условия:
— Удалённая работа.
— Полная занятость или контракт.
Это практическая инженерная роль с ответственностью за дизайн агента, реализацию, оценку, деплой и надёжность в продакшене.
Location: Remote (Peru)
Zeal is an AI-enabled software consultancy purpose-built for Fortune 1000 companies,
and we’re now part of Livefront
. We help companies navigate technology to drive business outcomes by attracting, retaining, and growing exceptional talent and empowering them to use innovative technologies and process frameworks.
We’re a values-driven technology company grounded in kindness, generosity, and integrity. Our mission is to build a place where our employees love their future and where clients trust us to deliver what we promise: to improve their business through technology. Love your future.
We’re looking for an outstanding Agentic Engineer to join our team. This role is available across our primary LATAM hub in Peru.
Who you are
You are a pragmatic, hands-on engineer who has built and shipped agentic AI systems into production. You understand that getting an agent to work is only part of the challenge. You know how to build systems that continue to work safely and reliably with real data, enterprise security requirements, and meaningful consequences when something goes wrong. You communicate clearly with clients and technical peers, make thoughtful architectural decisions, and are comfortable explaining why an agent behaved the way it did. You have strong software engineering fundamentals and the judgment to recognize when an agent is the right solution and when a simpler, deterministic approach is better.
What you will be doing
Work directly with clients to understand complex business problems and translate them into scalable, production-ready agentic AI solutions.
Design and implement multi-step agent systems, including orchestration, tool and function calling, task decomposition, and, when appropriate, multi-agent coordination.
Build integrations between agents and enterprise systems by exposing APIs as tools, implementing MCP servers, and developing structured tool contracts.
Design evaluation frameworks, guardrails, grounding and citation checks, and human-in-the-loop workflows that identify and manage agent failures before they reach users.
Instrument agent systems for traceability and observability, including agent actions, model behavior, token and cost usage, latency, and system performance.
Design and maintain state and memory across long-running workflows and implement model routing, retries, idempotency, and other patterns required for reliable production systems.
Build and deploy AI solutions using cloud platforms and services such as:
Azure OpenAI, Azure AI Foundry, Azure AI Search, AKS, or related Azure technologies;
Amazon Bedrock, Lambda, ECS, EKS, or related AWS technologies.
Apply strong software engineering practices using Python, Java, APIs, containers, source control, automated testing, and CI/CD.
Work directly with client engineering and security teams through architecture reviews, threat modeling, security reviews, audits, and other enterprise delivery requirements.
Evaluate when agentic architectures are appropriate and when deterministic pipelines, traditional machine learning, or other approaches are more reliable and cost-effective.
Turn successful approaches from client engagements into reusable patterns and solutions that can be applied across Zeal.
Build trust with clients and internal teams through strong communication, technical judgment, problem-solving, and execution.
Why you should apply
You want to work with passionate, talented people who are always looking for ways to make things better.
You value a work environment where kindness, mutual trust, and egoless collaboration are paramount.
You have a history of keeping promises, doing what is right, and spending energy on what matters.
You enjoy the variety and growth that comes with consulting for Fortune 1000 companies across industries and technical stacks.
You want to work on projects that have outsized impact and reach.
You believe in sweating the details, committing to quality, and taking pride in going the extra mile.
What you bring to the table
We expect candidates to demonstrate a strong software engineering foundation, hands-on experience building agentic AI systems in production, and a keen interest in consulting.
Agentic AI:
Hands-on experience designing and shipping production agent systems involving tool and function calling, multi-step workflows, orchestration, task decomposition, or multi-agent architectures. You can explain the architectural decisions you made, what failed, and what you learned.
Evaluation & Reliability:
Real-world experience evaluating agent behavior and measuring system failures, including building evaluation harnesses, guardrails, grounding checks, human-in-the-loop controls, and other mechanisms that prevent or mitigate errors.
Cloud Technologies:
Deep hands-on experience with either Azure or AWS and the AI and infrastructure services surrounding them, such as Azure OpenAI, AI Foundry, AI Search, AKS, Amazon Bedrock, Lambda, ECS, or EKS.
Software Engineering:
Strong proficiency in Python or Java, API design, containers, automated testing, source control, and CI/CD, with enough machine learning knowledge to determine when traditional ML or deterministic approaches are more appropriate than an LLM.
Enterprise Delivery:
Experience delivering software within large organizations and working through requirements such as role-based access, data isolation, security reviews, compliance, change control, and production governance.
Agent Observability:
Experience designing systems for traceability, state and memory management, model routing, latency and cost visibility, retries, idempotency, and other operational concerns associated with production agent systems.
Communication:
Excellent verbal and written communication skills and the ability to explain complex AI systems, architectural decisions, risks, and tradeoffs to both technical and non-technical stakeholders.
Problem-Solving:
Strong technical judgment and a demonstrated willingness to challenge assumptions, including recognizing when an agentic solution introduces unnecessary complexity and a deterministic approach would be more appropriate.
Experience with MCP and emerging tool-interoperability standards, evaluation frameworks such as RAGAS, fine-tuning, model distillation or optimization, and highly regulated industries such as financial services, insurance, healthcare, or manufacturing is helpful, but not required.
What to expect
When applying, please include a short note about yourself, a summary of your work experience, and a link to any public profiles you actively maintain (e.g., GitHub, LinkedIn). Our hiring process moves quickly and consists of several stages for candidates who capture our attention with their initial submission, sometimes including but not limited to a short preliminary phone interview, a series of video interviews, and a short take-home exercise, which you'll have up to a week to complete.
Additional information
We go out of our way to evaluate all employees and job applicants equitably based on merit, competence, and qualifications. We encourage candidates from all backgrounds and identities to apply, and we consider every applicant with an open mind. Don't worry, every application will be reviewed by a human.
Задачи:
— Разработка production-ready AI, LLM и agent-based решений.
— Управление полным циклом разработки AI: архитектура, реализация, тестирование, деплой и эксплуатация.
— Интеграция компонентов на базе LLM с детерминированной логикой, Context Engineering и Harness Engineering.
— Разработка Tool Calling Loops и подключение API, backend-сервисов и корпоративного ПО.
Требования:
— Минимум 3 года опыта создания и поддержки production AI приложений на базе LLM.
— Не менее 3 лет практического опыта в Agentic Engineering, включая дизайн, реализацию, интеграцию, деплой и поддержку AI агентов.
— Опыт разработки Tool Calling Loops и интеграции с API и backend.
— Опыт интеграции LLM-компонентов с Context Engineering и Harness Engineering (минимум 1 год).
— Знание MCP и корпоративных AI интеграций.
— Опыт с RAG-решениями и разработкой LLM приложений.
— Умение управлять полным циклом AI разработки.
— Отличные коммуникативные навыки для взаимодействия с командами и бизнес-стейкхолдерами.
— Наличие минимум 2 проектов с подтверждённым опытом коммуникации со стейкхолдерами.
Дополнительные преимущества:
— Знания в области AI governance, безопасности, комплаенса и защиты данных.
— Опыт работы с инструментами мониторинга AI, такими как Langfuse, Arize и аналогичными.
— Опыт с корпоративными AI экосистемами, AI шлюзами, управлением жизненным циклом prompt и governance моделей.
— Понимание дизайна мультиагентных систем и оркестрации агентов.
— Более 2 лет опыта с RAG и MCP серверами.
— Знакомство с AWS и AWS Kiro.
— Опыт внедрения AI guardrails и мер безопасности.
— Знание CI/CD и практик автоматизированного тестирования.
Условия:
— Контракт до 31 декабря 2029 года с возможностью продления.
— Полная занятость.
— Полностью удалённая работа в пределах ЕС.
— Требуемый уровень английского C1.
— Старт как можно скорее.
Требования:
— 5+ лет в Data Analytics / SaaS
— Эксперт в SQL, Python, dbt, Looker
— Моделирование данных, Analytics Engineering
— ETL/ELT процессы
— A/B тестирование, дизайн экспериментов
— Продуктовая аналитика
— Метрики SaaS (MRR, NDR, Expansion, Contraction)
— Квазиэкспериментальный анализ
— AI / MCP
Плюсом будет опыт в Data Science, ML, уровень Staff/Principal.
Условия:
— Зарплата 3200-3700$ гросс
— Работа только для фрилансеров
— Аустафф и рекрутинговые компании не рассматриваются
Требования к языку: английский B2
Локация: CET ±1, без России и Беларуси.
Задачи:
— самостоятельная разработка функционала платформы на Python
— тестирование нового функционала
— самостоятельное участие в процессах и решение средних и сложных задач
— анализ ТЗ и согласование планов выполнения работ для текущих задач
— обнаружение дефектов и повышение качества программного продукта
Требования:
— опыт коммерческой разработки бэкенд-разработчиком от 4-х лет
— опыт разработки решений в монолитной и микросервисных архитектурах
— понимание принципов взаимодействия с LLM, MCP-серверами
— опыт работы с реляционными БД и SQL, векторными базами данных
— опыт работы с FastApi
— опыт работы с системами управления версиями GIT
— базовые знания и опыт работы с системами Continuous Integration
— проактивность при выполнении рабочих обязанностей
— развитые коммуникационные навыки
— будет плюсом: опыт разработки AI-агентов, использование протокола A2A
УдалённоmiddleГеография найма не уточнена
Удалённо
middle
География найма не уточнена
Не хотите искать каждый день?
Настройте подбор один раз, и подходящие вакансии будут сами приходить в Telegram.
Настройте подбор, и подходящие вакансии будут приходить в Telegram.
Автоотклики