Jan Kislinger

About Me

I built my career on mathematics and statistics, first applying them in data science and now in ML engineering. At Sky, I design production systems while working closely with teams that develop and evaluate models. I’m also pursuing a PhD in recommender systems at Czech Technical University, where I bring together mathematics, computer science, and user research to study whole-page recommendations.

Resume

Download PDF

Experience Highlights

📅 Senior MLE @ Sky (Mar 2026 – Present): Designing end-to-end production ML systems in close collaboration with data science teams.
📅 Data Science Manager @ Sky (Apr 2024 – Feb 2026): Led a team of 4 building personalized sports recommendation pipelines.
📅 Data Scientist @ Sky (Jun 2023 – Mar 2024): Localized and deployed recommender models across international markets.
📅 Tech Lead @ Showmax (May 2020 – May 2023): Architected end-to-end ML pipelines (Airflow, Redis) for content personalization.
📅 Data Science Lead @ Oddin.gg (Jul 2018 – Apr 2020): Developed real-time e-sports ML models via gRPC servers.

Education & Skills

🎓 PhD Informatics @ Czech Technical University (2024 – Present)
🎓 MA Probability, Statistics & Optimization @ Charles University (2017)
🎓 BA Financial Mathematics @ Charles University (2014)

Technical Stack

Python TensorFlow PyTorch Polars Rust SQL Flask

Latest Blog Posts

Whole-Page Optimization, One Year Later

November 5, 2026

At RecSys 2025 I had the only paper on building a whole recommendation page. At RecSys 2026 there were four. I read them as a map of where the problem moved, and of the part I am still working on.

I Was Wrong About Git Worktrees, Twice

October 28, 2026

I used to dismiss Git worktrees as a waste of disk space I had no use for. Then uv made separate Python environments cheap, AI coding agents gave me a reason to work in parallel, and I went all in, until I found out that my brain is still single-threaded.

Recommender Systems in the Age of Generative AI

May 7, 2026

At ML Prague 2026, Bogdan and I led a workshop on how recommender systems can be improved with generative models. We covered extending item metadata and transformer-based recommendation models, and planned to discuss generating a whole page.