Ard Oerlemans
Software Engineer at Google DeepMind
Amsterdam, North Holland, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolArd Oerlemans is a software engineer with over a decade of applied computer vision and machine learning experience, currently working at Google DeepMind after a long tenure across Google teams focused on real-time video/audio communications and ML-driven video analysis. He holds a PhD in Computer Science from Leiden University and has deep practical roots in C++, Python and image/video processing from roles building ANPR, fisheye dewarping, video stitching and VMS server software. Ard contributes to high-profile open-source projects—most notably implementing and optimizing MoveNet pose detection within TensorFlow.js—bridging research-quality models to real-time web deployment. Known for refactoring and performance-minded engineering, he combines academic rigor with production-grade system design and a knack for turning complex vision algorithms into robust, low-latency services.
5 years of coding experience
22 years of employment as a software developer
M.Sc. Computer Science, M.Sc. Computer Science at Leiden University, M.Sc.Ph.D. Computer Science, Ph.D. Computer Science at Leiden University, Ph.D.Gymnasium, Gymnasium at Groene Hart Lyceum Alphen a/d Rijn
Dutch, English
Github Skills (6)
tensorflowjs10
computer-vision10
tensorflow10
machine-learning-models10
model-optimization10
javascript9
Programming languages (2)
Github contributions (5)
tensorflow/tfjs-models
Apr 2021 - Aug 2021
Pretrained models for TensorFlow.js
Role in this project:
ML Engineer
ML EngineerContributions:75 reviews, 28 commits, 47 PRs in 5 months
Contributions summary:Ard's commits primarily focus on implementing and improving the MoveNet pose detection models within the TensorFlow.js models repository. They added the MoveNet model to the Pose Detection API and implemented its core functionality and supporting files. The user refactored and optimized the MoveNet code, including applying keypoint filters, and integrated the model into the pose demo. They also addressed code review comments and incorporated the latest versions of the MoveNet models.
javascriptmachine-learningpretrained-modelstensorflowtensorflow-js
ardoerlemans/tfjs-models
Mar 2021 - Aug 2021
Pretrained models for TensorFlow.js
Contributions:122 pushes, 24 branches in 5 months
javascriptmachine-learningpretrained-modelstensorflowtensorflow-js
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.