Job description
Role overview
This role focuses on building scalable AI applications and LLM pipelines with emphasis on production-grade systems. Responsibilities include developing Python applications using FastAPI, managing LLM workflows via OpenAI SDK/LangChain, and implementing prompt engineering techniques. Key priorities include system observability and modern development practices.
Key technologies
Python, FastAPI, OpenAI SDK, LangChain, LangGraph, and async programming patterns.
Responsibilities
- Develop production-grade Python applications using FastAPI and async patterns
- Build and maintain LLM pipelines with OpenAI SDK, LangChain, or LangGraph
- Implement prompt engineering techniques including structured outputs and HITL design
- Ensure LLM observability through monitoring and debugging tools
- Design scalable architectures for AI application deployment
Requirements
- Python proficiency with FastAPI experience
- Knowledge of LLM pipeline development using OpenAI or similar frameworks
- Prompt engineering and HITL implementation skills
- Experience with async programming patterns
- Understanding of system observability practices
Benefits
- Work with cutting-edge AI/LLM technologies
- Collaborative team environment in Frankfurt
Keywords
PythonFastAPILLMOpenAI SDKLangChainPrompt EngineeringAIObservabilityProduction ApplicationsAsync Programming