Tom Decroos

Senior Software Engineer at Meta

Asse, Flemish Brabant, Belgium
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Tom Decroos is a Senior Software Engineer with 11 years of experience bridging cutting-edge ML research and production integrity systems, currently detecting and removing imposters across Facebook and Instagram at Meta. He holds a summa cum laude PhD in Computer Science from KU Leuven where his award-winning research applied AI to soccer analytics and produced widely used open-source packages (socceraction, matplotsoccer). Tom combines deep research credentials—papers at AAAI, KDD and ECML/PKDD—with hands-on engineering, improving build, documentation and maintainability in open-source projects. He has production ML experience from internships in ads recommendation to scaling integrity models at Meta, with a pragmatic focus on robustness and privacy. Based in Asse, Belgium, he brings a rare mix of academic rigor and large-scale product impact, often tackling the messy infrastructure and docs work that makes data science reusable.
code11 years of coding experience
job9 years of employment as a software developer
bookBachelor's Degree, Computer Science, 76%, Bachelor's Degree, Computer Science, 76% at KU Leuven
languagesEnglish, Dutch, French
github-logo-circle

Github Skills (9)

pandas10
python10
data-science9
documentation9
numpy8
tqdm6
scikit-learn6
scikit6
lxml5

Programming languages (2)

Jupyter NotebookPython

Github contributions (5)

github-logo-circle
ML-KULeuven/socceraction

Jul 2019 - Jan 2021

Convert soccer event stream data to SPADL and value player actions using VAEP or xT
Role in this project:
userData Scientist
Contributions:27 commits, 13 PRs, 61 pushes in 1 year 6 months
Contributions summary:Tom primarily focused on refactoring and improving the project's build and documentation processes. They removed an unnecessary dependency (`ujson`) across multiple files related to data loading from different soccer data sources. Additionally, they spent significant effort trying to resolve issues with the automated documentation generation using Read the Docs, indicating a focus on improving the project's usability and maintainability, likely for other Data Scientists.
data-streamevent-streamsoccerstreamsports-analytics
TomDecroos/matplotsoccer

Jul 2019 - Apr 2020

Package to visualize soccer data
Contributions:4 commits, 9 pushes, 1 branch in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Tom Decroos - Senior Software Engineer at Meta