Machine Learning & Data Science researcher with a Ph.D. in Medical Imaging and years of R&D and consulting experience. I solve real-world problems by crafting state-of-the-art algorithms and turning them into robust, community-driven Python libraries 🐍. Passionate about open source, reproducible research, and scalable ML infrastructure.

• Create & maintain several open-source Python packages used by thousands of developers
• Contributed code, CI/CD pipelines, issue reports & reviews across the ML ecosystem
• Strong focus on testing, automation, and developer experience — from pre-commit hooks to GitHub Actions
• achieved top-tier rankings across notebooks, competitions, and datasets, applying practical ML skills to real-world challenge problems and sharing my findings

• Built and led a team to deliver a scalable video-analysis platform from prototype to production
• Director of Open Source at Lightning AI — led the OSS team for 3+ years, driving feature roadmaps, release cycles, and cross-team coordination across PyTorch Lightning, TorchMetrics, and the broader Lightning ecosystem. Mentored contributors, scaled community engagement, and ensured quality across 10+ active repositories
• LinkedIn Learning certified in Leadership Foundations, Leadership: Practical Skills, and Leading Your Team Through Change

• Ph.D. in Medical Imaging — Czech Technical University in Prague
• 15+ journal articles & 20+ conference papers (ISBI, ICIP, ACCV, MICCAI workshops)
• Reviewer for IEEE TMI, TCIA and major international conferences
• Co-organized the ANHIR challenge on histological image registration

Long-term open-source contributor and maintainer. My work spans ML frameworks, developer tooling, and computer vision — always aiming to make research more reproducible and engineering more enjoyable.

Active projects I maintain:

• 👁️ supervision The go-to Python toolkit for plugging any detection or segmentation model into real-world CV pipelines. Unlike framework-specific tools, it works with YOLO, Transformers, or any custom model out of the box — providing a unified API for tracking, filtering, annotating, and chaining operations that would otherwise require glue code.

• 🎯 RF-DETR A new take on real-time object detection that brings transformer accuracy to YOLO-level speeds. Stands out by matching or beating state-of-the-art on COCO while being straightforward to fine-tune on custom datasets — no complex anchor tuning or NMS hacks needed.

• ♻️ pyDeprecate Born from the pain of managing API changes in large libraries like PyTorch Lightning. A zero-dependency tool that lets library authors deprecate, rename, and redirect functions or classes with automatic call forwarding — so users get clear migration warnings instead of silent breakage.

• 🗄️ cachier Unlike functools.lru_cache, cachier persists results across sessions and even across machines. Ideal for caching expensive computations like API calls or data processing — supports MongoDB and file-based backends with built-in staleness handling, so cached results stay fresh without manual invalidation.

• 📈 pyRepoStats Fills the gap between git log and full analytics platforms by generating quick contribution stats that include issues and PR activity. Built for maintainers who want a lightweight health check on their projects without setting up dashboards.

Emeritus maintainer — projects I co-created and still partially supervise:

• ⚡ PyTorch Lightning The most widely adopted framework for scaling PyTorch — used by thousands of teams from academic labs to Fortune 500 companies. Eliminates training loop boilerplate and lets the same code run on a laptop GPU or a 10,000-GPU cluster without changes, bridging the gap between research prototypes and production systems.

• 📏 TorchMetrics The standard metrics library for the PyTorch ecosystem, solving the surprisingly hard problem of computing correct metrics in distributed training. Ships 100+ metrics for classification, regression, NLP, and retrieval — all with automatic accumulation and device synchronization that just works across multi-GPU setups.

Notable contributions to other projects: ultralytics/YOLOv5, DIPY and more...

If you find my open-source work useful, consider sponsoring me 💚 I'm also available for consulting & contract work in ML, MLOps, and Python engineering — see SUPPORT.md for details.