Сравним вакансию с вашим действующим резюме и составим письмо под эту роль.
Описание вакансии
Коротко о роли
What you'll do Agentic engineering Architect and build a production multi-agent system that can safely take actions across Distru and our customer’s core systems Iterate and maintain the MCP that connects Distru to Claude & Codex. Own reliability, observability, and durable execution end to end.
Responsibilities:
— Architect and build a production multi-agent system that safely operates across Distru and customers' core systems.
— Iterate and maintain the MCP connecting Distru to AI tools like Claude and Codex.
— Own reliability, observability, and durable execution end to end for the AI harness.
— Write evaluation suites to improve agentic systems based on real customer use cases.
— Build a unified data system aggregating multiple data sources into a singular layer exposed via MCP.
— Develop a contextual memory system that ingests customer data to enhance agent performance.
— Set architectural standards for building, testing, and shipping agents, guiding the engineering team.
— Keep pace with latest agentic frameworks, toolkits, and models; rapidly prototype new ideas.
— Improve engineering workflows including hands-on use of Claude Code and similar tools.
Requirements:
— 7+ years of full-stack development experience, ideally in B2B SaaS.
— Hands-on experience building multi-agent harnesses in production.
— Experience building MCPs used in production.
— Strong understanding of reliability, observability, permissions, and safe workflow execution.
— Experience operating as both product and engineering lead, comfortable with scoping and decision-making.
— Proficiency in React, TypeScript, Node, PostgreSQL, GraphQL, and LangGraph.
— Experience working in early-stage startups (under 20 engineers) with ability to set direction amid ambiguity.
— Team-first attitude with low ego and strong communication skills.
Preferred:
— Background in supply chain, ERP, CRM, B2B marketplace, or accounting software.
— UX design experience.
— Experience with agentic systems beyond basics, such as evaluation frameworks or agent-to-agent protocols.
— Experience using Claude Code or similar tools to build products independently.
— Cannabis industry experience.
Benefits:
— Fully remote position across 4 continents.
— Employee-friendly option terms with a 10-year exercise window after 2 years.
— 18 days PTO plus 11 holidays (excluding sick days).
— Medical, dental, vision, and 401(k) for US employees.
— Access to best AI tools and a generous AI stipend.
— Yearly in-person team offsites.
Interview process includes written application questions, recruiter screen, technical interview, take-home harness spec, and review with engineers.
Salary range: $200,000 - $300,000 per year depending on experience and skills.
Контакты работодателя доступны по кнопке «Откликнуться» после входа.
80/100
Хорошая вакансия
Оценка от Job Hunters AI
Staff AI Product Engineer; понятные задачи; прозрачная оплата; гибкий формат; современный стек.
Из чего сложилась оценка. Нажмите, чтобы узнать подробнее
Понятные задачи
Задачи подробно описаны: архитектура и разработка мультиагентной системы, поддержка MCP, обеспечение надежности и наблюдаемости, написание evals, построение единой системы данных и контекстной памяти, стандарты архитектуры.
Из объявления
You'll own the architecture and technical direction of our AI product suite, partnering with our Director of AI Engineering, including: Agentic harness: a multi-agent system that safely operates across a business's core tools (ERP, CRM, spreadsheets, calendars, email, analytics, compliance systems) MCP: our MCP that connects Distru to external AI harnesses Context Layer: our context layer that ing
Мэтч и сопроводительное
Сравним вакансию с вашим действующим резюме и составим письмо под эту роль.
Зарплаты и спрос: AI-инженер (LLM, агенты, AI product)
Сейчас в каталоге 881 вакансия по этому направлению, удалённо можно работать в 44%.
Середина вилки в этой вакансии, 250 000 $ в год, на 11% выше медианы по направлению (225 000 $). У половины вакансий от 200 000 $ до 280 000 $ (вакансий с вилкой: 69).
Навыки этой вакансии, которые чаще всего просят по направлению: PostgreSQL (5%). В скобках доля вакансий направления.
Автоотклики