Software & AI Expert building intelligent systems

Berlin-based engineer with 10+ years of experience across E-Commerce, Manufacturing, Industry, and Trade sectors. I specialize in transforming data challenges into production-ready AI solutions—from serverless GenAI platforms that automate rankings across 26 clients, to privacy-compliant RAG systems that save 60-70% research time. I thrive in cross-functional teams and deliver full-stack solutions from data infrastructure to AI deployment.

What I'm doing right now

  • AI Engineer consultant building GenAI platforms and intelligent agent systems
  • Architecting serverless multi-tenant data platforms with API-first architecture
  • Developing Model Context Protocol (MCP) servers for model-agnostic CRM integration
  • Building containerized on-premise RAG systems for privacy-compliant knowledge management

Track record

  • Designed and implemented fully automated, serverless GenAI data platform serving 26 clients with multi-LLM support
  • Built privacy-compliant on-premise RAG system achieving 60-70% research time savings
  • Developed event-driven alerting systems reducing reaction times from days to real-time
  • Architected MLOps frameworks on Databricks enabling parallel model training and efficient deployment
  • Migrated BI infrastructure from on-premise to hybrid cloud, establishing "Single Source of Truth"

How I like to work

  • End-to-end ownership: from exploratory data analysis through model development to production deployment
  • Start with the problem, baseline with metrics, build MVPs, iterate based on feedback
  • Focus on scalable, maintainable solutions with proper MLOps practices
  • Bridge technical implementation with business requirements
  • Prefer containerized, cloud-native architectures for flexibility

Stack and tools I reach for

Data Science & AI

  • Python, Transformers, HuggingFace, OpenAI, LLM
  • Agent frameworks: PydanticAI, LangGraph, LangChain
  • RAG systems: Qdrant, Weaviate, Milvus, ChromaDB
  • ML: TensorFlow, PyTorch, Scikit-learn

Data Engineering

  • Cloud: Azure, GCP (VertexAI, Cloud Run, BigQuery), AWS (CDK)
  • Orchestration: Databricks, Airflow
  • Processing: PySpark, dbt
  • DevOps: Docker, Terraform, CI/CD pipelines

Software & Infrastructure

  • Languages: Python, Go, SQL
  • Tools: Git, Nix, Linux
  • Databases: PostgreSQL, NoSQL, Vector DBs

Business Intelligence

  • Visualization: Tableau, Looker, Power BI, Qlik
  • Analytics: Google Analytics, Statistical Analysis