Data Engineer · Berlin, Germany

Reliable data systems and AI integration for teams that need production-grade results.

Data Engineering and AI systems — batch pipelines, knowledge retrieval, and workflow automation.

I build deterministic, observable, production-grade data and AI systems. Grounded in enterprise batch ETL engineering, expanding into RAG pipelines, embeddings, and AI-driven automation.

Currently building

AI and automation projects

Expanding from production batch ETL into applied AI systems — RAG pipelines, embeddings, and workflow automation.

Document Q&A System

In progress

Embedding-based retrieval system over structured documents. Exploring chunk-level metadata handling and source attribution in retrieval responses.

Python OpenAI API pgvector

Full RAG Pipeline

Planned

End-to-end RAG system from document ingestion to grounded response generation. Focus on deterministic chunking strategies and retrieval evaluation.

Python LangChain pgvector OpenAI API

AI Workflow Automation

Planned

Email classification and task-routing pipeline using LLM inference with structured outputs for CRM integration.

Python OpenAI API LangChain

Who I help

Data Engineering + AI Systems

Engineering teams and departments running batch-heavy reporting, large document knowledge bases, or manual data workflows that block AI adoption.

  • Pipelines that fail silently or require manual restarts
  • Reporting data that stakeholders cannot trust
  • Enterprise knowledge bases that AI systems cannot reliably query
  • Data workflows requiring constant manual intervention