We are seeking a Python GenAI Engineer to design, implement and maintain scalable AI-powered applications, focusing on seamless integration of OpenAI APIs and collaboration with cross-functional teams to automate deployment, monitoring and optimization of AI-driven workflows.
Responsibilities
- Develop and optimize backend services based on integrations with AI/LLM applications
- Implement CI/CD pipelines for automated deployment
- Monitor and optimize AI-powered services
- Ensure observability and logging for LLM API performance tracking
- Work with cloud environments for hosting and scaling AI applications
Requirements
- Primary skill: Python.Web
- Must-have skills:
- Strong Python backend engineering (FastAPI, Flask)
- LLM API integration
- Prompt engineering
- Agentic workflows and orchestration (LangChain, LangGraph, Pydantic AI, etc.)
- Handling LLM limitations: latency, cost control, retries, fallbacks
- Working knowledge of SQL/NoSQL databases, Redis, Kafka
- Experience with MCP
- Advanced English communication skills (B2 level)