Miguel Méndez is a Senior Machine Learning Engineer based in Vigo, Spain, with nine years of hands-on experience building and deploying computer vision and deep learning systems. He has led end-to-end ML efforts from research to production—optimizing models for edge and cloud, architecting MLOps pipelines, and delivering real-time analytics for thousands of sports matches across 90+ leagues. At Hudl and previously at StatsBomb and Gradiant he focused on player tracking, ball detection, semantic segmentation and camera calibration, often adapting PyTorch models for constrained deployments like Nvidia Jetson. An active contributor to the OpenMMLab mmsegmentation project, Miguel has improved loss functions, visualization hooks and compatibility with modern ML engines, highlighting a practical attention to reproducibility and maintainability. His academic background in AI from Purdue and UPC complements a pattern of translating research methods (time-series and multisensor classification) into robust production systems.
9 years of coding experience
7 years of employment as a software developer
Bachelor of Engineering (B.E.) Computer Engineering (Study abroad), Bachelor of Engineering (B.E.) Computer Engineering (Study abroad) at University of Stavanger
Master’s Degree Artificial Intelligence (Study Abroad), Master’s Degree Artificial Intelligence (Study Abroad) at Purdue University
UPC Universitat Politècnica de Catalunya
Bachelor's Degree Computer Engineering, Bachelor's Degree Computer Engineering at Universidade da Coruña
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Role in this project:
ML Engineer
Contributions:1 review, 4 commits, 8 PRs in 8 days
Contributions summary:Miguel primarily focused on modifying and improving the semantic segmentation models and related tools within the mmsegmentation library. Their contributions involved fixing bugs related to loss functions, customizing the visualization hook, and updating the codebase to utilize the `resize` function across multiple modules. The user's work included refactoring code, correcting typos, and ensuring compatibility with the latest mmengine library. These changes collectively enhanced the usability and maintainability of the segmentation models.
Contributions:4 reviews, 75 PRs, 208 pushes in 4 years 10 months
javascriptreactweb-personal
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
Miguel Méndez - Senior Machine Learning Engineer at Hudl