Senior Data & AI Engineer (GenAI / LLM)

Our end client, an enterprise company in the DACH region, is expanding its central data platform and moving its first GenAI use cases (internal knowledge assistant, document intelligence) from pilot into production. They are looking for a Data & AI Engineer who can build both robust data pipelines and production-ready LLM applications — not just prototypes.

Tasks

• Design and develop scalable data pipelines (batch and streaming) on a lakehouse architecture
• Build production-ready RAG systems: chunking strategies, embeddings, vector retrieval, answer evaluation
• Integrate LLM APIs (OpenAI, Anthropic, Google), including function calling and structured outputs
• LLMOps: deployment, monitoring, cost tracking, guardrails, and evaluation pipelines
• Implement solutions in line with GDPR and the EU AI Act in collaboration with Data Governance and Legal
• Data modeling and building curated data products for business teams

Must-have skills

• 6+ years in Data Engineering, including 2+ years with LLM/GenAI applications in production
• Senior-level Python, very good SQL
• Modern data stack: dbt, Airflow or Dagster, Spark
• Databricks or Snowflake (lakehouse/warehouse architecture)
• RAG stack: vector databases (pgvector, Weaviate, Qdrant or similar), embedding models, orchestration with LangChain/LlamaIndex or a custom framework
• Hands-on experience with LLM APIs (OpenAI, Anthropic Claude, Google Gemini)
• MLOps fundamentals: MLflow, containers, CI/CD; Azure ML or Vertex AI

Nice-to-have

• LLM evaluation with Ragas, promptfoo, or custom eval frameworks
• Fine-tuning / PEFT (e.g. LoRA) and experience with open-weight models
• Streaming with Kafka
• Kubernetes and Terraform
• Experience with EU data residency requirements (EEA cloud setups)