AI / LLM Engineering (Werkstudent)

CognitX AI GmbH is building a privacy-first AI advisor. As a Working Student in AI/LLM Engineering, you'll design and evaluate Agentic AI systems, build agentic workflows, implement adapters, and optimize prompts. You'll work with Python, FastAPI, Docker, and Kubernetes, and contribute to evaluation metrics. This role offers mentorship from senior AI experts and flexible remote work.

• Build and improve agentic workflows (tool/function calling, planning, self-checks) for analytics, summaries, visualizations, and task automation.
• Implement adapters/tools to connect LLMs with internal and external services.
• Contribute to FastAPI backend with clean interfaces, validation with Pydantic, and tests.
• Develop evaluation metrics to measure accuracy, latency, and cost.
• Optimize prompts, retrieval/contexting, and execution strategies for privacy, reliability, and performance.
• Ship in containers (Docker) and collaborate on deploys (Kubernetes), CI, and observability.
• Document decisions and share learnings with the team.

• Experience with LLMs/AI agents (function/tool calling, RAG, MCP, or agent frameworks) and Machine Learning fundamentals.
• Strong Python skills for production code and data work (typing, tests, packaging).
• Familiarity with APIs and microservices (FastAPI preferred), Git, and containerized dev (Docker).