Назад до пошукуAI Engineer (Senior/Lead)
Віддалений* формат співпраці з території - Україна: Львів
*Ви можете працювати віддалено з території країни (або країн), для яких відкрита ця позиція.
AI Engineering& інші навички
Не знайшли свою вакансію?
Поділіться своїм CV — ми запропонуємо роль, що відповідає вашим навичкам та досвіду.
Знайти мою роль →We are looking for a Senior/Lead AI Engineer to design, build and operationalize production-grade AI agents, multi-agent workflows and AI/ML solutions using Python, Azure AI Foundry, Semantic Kernel / Microsoft Agent Framework, LangGraph, LangChain, AutoGen and Strands SDK. You will work alongside architects and data teams to take solutions from prototype to scalable, reliable production.
Чим ви будете займатися у цій ролі
- Design, build and maintain production-grade AI agents and multi-agent workflows for enterprise use cases
- Integrate and operationalize AI/ML models and agent workflows into scalable production systems
- Implement orchestration using Semantic Kernel / Microsoft Agent Framework, LangGraph, LangChain, AutoGen and/or Strands SDK
- Implement RAG, grounding and prompt optimization to improve response quality and reduce hallucinations
- Integrate agents with internal and external systems via APIs and connectors
- Design and implement error handling, fallback flows and escalation paths
- Perform testing and evaluation of agents and automation workflows
- Collaborate with architects and data teams to translate requirements into deployable AI solutions
- Support deployment, CI/CD and release management (Azure DevOps)
- Monitor and continuously improve agent performance, reliability and cost efficiency
Навички
- 5+ years of experience in strong Python development for AI/agent solutions, with solid general scripting ability
- Hands-on experience building agents and multi-agent workflows with one or more orchestration frameworks: Semantic Kernel / Microsoft Agent Framework, LangGraph, LangChain, AutoGen, Strands SDK
- Expertise in Azure AI Foundry for building, deploying and operating agents at scale (hosted agents, agent service, memory, evaluation)
- Understanding of LLM concepts: prompt engineering, RAG, grounding, tool/function calling, hallucination mitigation and evaluation
- Skills in API integration (REST APIs, JSON, authentication via OAuth2 / API keys)
- Experience designing agent behavior: state and memory management, tool use, error handling, fallback and escalation paths
- Comfort collaborating with architects and data engineering teams to deliver scalable, production-grade solutions
- English proficiency at B2 level or higher
Буде перевагою
- Experience with Azure AI Services and the broader Azure stack (Blob Storage, Container Services)
- Multi-cloud agent deployment experience (e.g., AWS Bedrock via Strands SDK)
- Familiarity with Model Context Protocol (MCP) for tool/connector integration
- Expertise in LLMOps / MLOps: monitoring, evals and cost/latency optimization for AI Agents
- Experience with vector databases, retrieval infrastructure for RAG, Docker and Microsoft Graph API integration, as well as delivering in enterprise or regulated/validated environments (e.g., GxP), including governance and observability tooling