Freelance AI engineering for organizations that want to move past the proof-of-concept. From intelligent agents and RAG systems to GenAI integrations that run reliably — including in security-sensitive environments.
My core focus. Autonomous, tool-using agents that take over real workflows — with the right guardrails, evaluation and human oversight where it matters. From orchestration to reliable execution in production.
Retrieval systems grounded in your documents and knowledge graphs. Answers that hold up, with citations and without the hallucination drama.
Embedding GenAI reliably into existing systems and processes — from API layer to monitoring, with cost and latency under control.
Systematically measuring whether AI does what it should: eval suites, regression tests and production monitoring. So you know an improvement is actually an improvement.
Thinking through where AI does and does not add value, which use cases come first, and how to get from experiment to roadmap.
A background in finance and R&D, now fully in AI engineering. That combination — rigorous research and working systems — shapes how I build: curious about what is possible, strict about what demonstrably works.
A concrete idea or still a fuzzy question — both are welcome. Drop me an email and we'll take it from there.