I design and build production AI systems — from ML and NLP applications to generative AI and private local-LLM infrastructure. My background in machine learning predates the generative-AI wave, so I use LLMs when they help rather than because they are fashionable.
I work across machine learning, language technology and software engineering — with deep technical involvement, pragmatic implementation and a preference for solutions that remain understandable, maintainable and useful in practice.
Custom ML/AI applications, APIs and product integration — from first technical validation to a shipped feature your users actually rely on.
Evaluation, monitoring, reproducibility and infrastructure — including open-source and self-hosted stacks that keep working after the demo.
Search, extraction, classification, assistants and text generation — using classical NLP, transformers and LLMs where they make sense.
Backends, databases, pipelines and supporting infrastructure — designed around maintainability and performance rather than unnecessary complexity.
Run modern open models on your own infrastructure. I help select models and hardware, build local RAG systems, optimize inference and deploy maintainable self-hosted stacks.
Concrete systems for real workflows, alongside tools I build and maintain in the open.
An AI assistant creates suitable hiking routes from individual preferences, taking gastronomy, personal limitations and additional requirements into account.
An AI-based workflow recognizes receipt contents, classifies them automatically and triggers subsequent processing steps in accounting software.
The assistant helps marketing teams gather all relevant campaign information in a structured way and produces consistent briefings in the company's language and brand style.
NLP methods applied with dida to software that detects potential errors in rental contracts and supports legal review.
A Python framework for building and managing multi-step LLM applications, with workflow management, prompt iteration, testing and evaluation.
A toolkit for identifying bias in NLP models and creating a practical entry point for impact assessment and mitigation work.
A graphical installer that guides people through installing alternative Android distributions without requiring the usual command-line setup.
A track record spanning research, competitions, production AI, open source, workshops and hands-on consulting.
Designing, implementing and operating ML, NLP and GenAI applications for companies — from prototype to production operation.
PromptMage, Biaslyze and other tools — supported through programs including Prototype Fund and Media Tech Lab.
Practical AI workshops, hackathons and technical training for teams.
Research as a student assistant at Humboldt University of Berlin and applied ML through international Kaggle competitions.
Conference talks, tutorials and podcast conversations — PyCon/PyData speaker since 2018.
Long-form articles from depends on the definition — still relevant, still referenced.
Need help prototyping an AI product, putting an ML system into production or running models locally? Tell me what you're working on.