With a background in Mathematics, I gradually specialized towards Software Development and Applied AI. These days, I especially enjoy the space between an interesting technical problem and a system that people can actually use, and I do so by building industry grade AI applications and by maintaining open-source research software.
Portfolio LinkedIn Google Scholar
My expertise spans applied mathematics, machine learning, and software development. I currently work across enterprise RAG, LLM evaluation, retrieval, and application delivery; previously, I built and evaluated forecasting systems. For the fuller story about my work and background, visit my portfolio website .
Here I are my main contributions to open-source projects, mainly built during my PhD years at KU Leuven.
An explainable-AI Python package that turns Random Forest predictions into a small set of representative rules. It supports classification, regression, survival analysis, multi-label, and multi-target problems.
- Evaluated across 89 datasets
- Packaged and released on PyPI
- Maintained with tests, documentation, tutorials, and GitHub Actions
- Open to feature ideas and contributions
A focused feature-attribution method for explaining time-to-event predictions over selected intervals. Will be released upon acceptance of the related paper.
A computer-vision workflow for measuring fibre directionality and dispersion in biomedical images.
| Area | Tools |
|---|---|
| Machine learning | Python, scikit-learn, scikit-survival, SHAP, XGBoost, PyTorch |
| Data and experimentation | pandas, Polars, SciPy, statsmodels, Optuna, Nixtla |
| AI applications | RAG, LLM evaluation, prompt engineering, Azure AI Foundry |
| Software delivery | Git, GitHub Actions, Linux/Bash, SQL, React, C#, Terraform, Streamlit |