AI engineer in LLM applications

We're hiring an AI Engineer (German speaker) for a global leader in life sciences and clinical diagnostics. You'll design, build and ship production-grade LLM applications, from RAG pipelines to AI assistants, deployed on Azure. You'll work in a fast-paced, AI-first engineering team using tools like Claude Code and Cursor daily, while keeping strong coding fundamentals.

• Build and deploy LLM-based applications (Anthropic Claude, Azure OpenAI, OpenAI or open-source models)
• Design RAG pipelines: embeddings, chunking, retrieval and vector stores
• Write clean, production-ready Python
• Deploy services on Azure with Docker and CI/CD pipelines
• Explain modelling decisions and trade-offs to non-technical stakeholders

• 2–5 years of professional software engineering experience, including 2+ years building and shipping ML/AI systems in production
• Hands-on LLM application deployment with a major model provider or open-source models
• Practical RAG and embeddings experience, with at least one production vector store (e.g. Azure AI Search, Pinecone, Weaviate, pgvector, Qdrant)
• Proficiency with AI coding tools such as Claude Code and Cursor, plus strong manual coding skills
• Python with PyTorch and/or TensorFlow, scikit-learn, pandas, NumPy
• Fluent German and English
• EU citizenship
• Bachelor's or Master's in Computer Science, ML, Data Science, Mathematics, Statistics or related field, or equivalent practical experience.
• Будет плюсом: Git, branching strategies and PR-based code review; CI/CD pipelines (Azure DevOps, GitHub Actions); Azure services (AKS, App Service, Functions, Azure AI/ML) and Docker; Experience in fully remote, globally distributed teams

• Fully Remote – candidates must be based in an EU country
• B2B Contract
• Urgent start