Javier Berneche
ML Manager at Tryolabs
Montevideo, Montevideo, Uruguay
Summary
🤩
Rockstar🎓
Top SchoolJavier Berneche is an ML manager with 11 years of hands-on experience building and scaling machine learning and backend systems from Montevideo, Uruguay. At Tryolabs he progressed from full-stack and IoT engineering to leading dozens of ML teams, advising startups and Fortune 200 clients across the US, Europe, and Asia on model experimentation and deployment. He has deep expertise in computer vision—delivering healthcare and fire-prevention solutions—and in retail price automation and optimization, and has presented at the Embedded Vision Summit in 2023 and 2024. Technically fluent with Python, async backends, AWS Lambda and production-grade ML infrastructure, he also contributes to open-source tooling such as the lightweight Norfair tracking library, improving core distance metrics and IoU robustness. Colleagues know him as a pragmatic leader who translates stakeholder goals into reproducible ML systems and reliable production services.
12 years of coding experience
12 years of employment as a software developer
Universidad de la República
Github Skills (4)
multi-object-tracking10
python10
numpy9
object-detection9
Programming languages (5)
Github contributions (5)
tryolabs/norfair
Jul 2022 - Jan 2023
Lightweight Python library for adding real-time multi-object tracking to any detector.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 release, 47 reviews, 112 commits in 5 months
Contributions summary:Javier primarily contributed to the `norfair` library by implementing and refining distance functions used for multi-object tracking. Their commits focused on adding new distance metrics like Frobenius, Manhattan, and mean Euclidean, as well as enhancing the IoU calculations for bounding boxes. Additionally, they addressed robustness issues within the IoU implementation and made changes to the Tracker class, indicating a focus on improving the accuracy and performance of the core tracking algorithms. The contributions highlight expertise in object tracking and related mathematical concepts.
multi-object-trackingpythontrackingtracking-algorithmkalman-filter
Exartu/Exartu-Pagination
Oct 2014 - May 2016
Contributions:62 commits, 20 pushes in 1 year 7 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.