AI Engineering · Software Quality
Building reliableAI-powered software.
I combine AI engineering, software architecture, and quality engineering to build reliable AI-powered systems.
Munich, GermanyAvailable for selected opportunities
Focus areas
AI Engineering
LLM applications, RAG, AI agents.
AI Quality
Evaluation, testing, reliability.
Test Automation
Scalable test systems, CI/CD.
Software Design
Architecture, clean code, system design.
Selected projects
All projectsRelynx Requirement Intelligence
AI · Atlassian Forge · TypeScript
AI-powered requirement analysis for Jira, helping teams improve requirement quality and derive structured engineering insights.
- TypeScript
- Atlassian Forge
- Jira
- LLM APIs
LLM Evaluation Lab
Python · LLM · Evaluation
A practical project for evaluating LLM outputs using reproducible tests, evaluation metrics, and representative examples.
- Python
- LLM APIs
- pytest
- Evaluation metrics
Latest writing
All articlesTesting RAG Applications: A Practical Guide
A retrieval-augmented generation system has two places to fail — retrieval and generation. A layered test strategy that isolates each, from unit tests to end-to-end evaluation.
2 min read
2 min read
Evaluating LLM Applications in Production
Offline test sets tell you whether a change is safe to ship; production signals tell you whether it keeps working. How to combine both into an evaluation practice for LLM features.
2 min read
2 min read
Building Reliable AI Applications
Reliability in LLM-based software is an engineering property, not a model property. A practical look at the boundaries, contracts, and feedback loops that make AI features dependable.
2 min read
2 min read