Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$70к$89кмедиана$108к
35 в выборке
На СНГ рынке: $4.3к/мес ($3.6к - $5к)
83
Хорошая вакансия
развернуть
Роль предполагает чёткую ответственность за развитие production-платформы на базе агентного ИИ, но нераскрытый клиент и консалтинговый формат оставляют меньше ясности о команде и долгосрочном проекте.
Клиент не назван
?Консалтинговый формат
Современный ИИ-стек
Чёткая зона ответственности
Техническое влияние
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Agentic AI Engineer (AI): Building and evolving a secure conversational analytics platform with an accent on agentic workflows, governed data integrations, and production-grade LLM features. Focus on designing extensible agent frameworks, developing MCP integrations, and implementing evaluation, observability, and security controls.
Location: Warsaw, Poland; hybrid
Company
hirify.global connects talent with product careers at high-growth companies; the client is a global management consultancy building AI-powered products for complex business challenges.
What you will do
Design, build, and evolve agentic AI workflows for data exploration, analysis, and conversational insights.
Develop an extensible agentic framework covering orchestration, reusable tools, skills, and conversation management.
Build secure integrations with application services and governed data sources, including sandboxed code execution and AI-powered visualizations.
Develop MCP servers and clients and configure client-specific prompts, tools, skills, and data definitions without duplicating core architecture.
Contribute to system architecture and migration of the LangChain-based solution.
Own features from technical design and implementation through production release and continuous improvement.
Requirements
6+ years of experience in software engineering, data analytics, or related fields, including 2+ years in agentic AI engineering.
Strong Python skills and experience building, testing, and maintaining production-grade applications.
Hands-on experience with agentic AI frameworks such as Pydantic AI, LangGraph, LangChain, or OpenAI Agents SDK.
Understanding of tool calling, multi-step orchestration, context management, guardrails, and human-in-the-loop workflows.
Experience with MCP, multi-agent systems, and cross-application integrations.
Experience developing AI agents for data analysis, including dataset exploration, code generation and execution, and result interpretation.
Strong system design and architecture skills, including configurable and extensible solutions and technical trade-off evaluation.
Understanding of AI security, evaluation, observability, secure data access, LLM testing, tracing, and performance monitoring.
Strong ownership, communication, cross-functional collaboration, and practical experience with AI coding assistants such as Claude Code or Codex.
Nice to have
Experience with Pydantic AI, Pydantic AI Harness, and LangChain, particularly framework migration.
Familiarity with SQL, pandas, DuckDB, Ibis, Azure OpenAI, Docker, Plotly, or Dash.
Experience in retail, pricing, promotions analytics, client-facing AI products, React, or FastAPI.
Culture & Benefits
Work on innovative AI-powered products at a globally recognized consulting firm.
Help shape the architecture and technical direction of an evolving agentic AI platform.
Build production AI solutions where accuracy, data security, and reliability are essential.
Collaborate with experienced engineering and product teams in an environment supporting experimentation, continuous improvement, and technical ownership.
Use modern tools including Pydantic AI, MCP, Claude Code, Cursor, and OpenAI Codex.
Hiring process
hirify.global recruiter interview, cultural fit interview, technical interview, final interview, and offer.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →