I am a machine learning engineer based in Innsbruck, Austria. My research interests are LLM training, evaluation, and reliable reasoning. My public work includes experiments with language models, AI agent security, and tools for coding agents.
I am a co-founder of enrik.ai, where I am building an AI-native go-to-market (GTM) platform. Previously, I led IT & software at Heliotherm, where I built an anomaly detection pipeline supporting predictive maintenance for more than 4,000 heat pumps. Before that, I developed embedded runtime analysis tools at Accemic Technologies and contributed to the COEMS and TRISTAN research programs.
I hold a BSc in Computer Science from the University of Innsbruck, where my MSc in Computer Science is in progress. My academic work focuses on deep learning for medical imaging: mammogram quality assessment and kidney and tumor segmentation. I bring that experimental background to my current work on language models, with an emphasis on baselines, ablations, and reporting what the evidence supports.
Recognition
I won a gold medal and placed 9th out of 4,211 in Kaggle's AI Agent Security — Multi-Step Tool Attacks competition.
I collaborated with Refractal AI, a London-based AI security startup, on the competition.
The public solution includes a technical working note and evaluation tooling for the submitted attack, reference defenses, and candidate search. The write-up documents the agent-assisted workflow, attribution, and limits of local replay.
Background
Tools I work with
- Languages
- Python, TypeScript, C++, C#, Java, SQL
- Machine learning
- PyTorch, TensorFlow, scikit-learn, NumPy, Pandas, OpenCV
- Software & infrastructure
- React, Next.js, PostgreSQL, Docker, GitLab CI/CD, Linux