Tyler Z
Principal Machine Learning Developer at Autodesk
Canada
Summary
🤩
Rockstar🎓
Top SchoolTyler Z is a Principal Machine Learning Developer with a decade of experience building production CV and ML systems, now leading Agents and LLM efforts at Autodesk after senior engineering and technical lead roles at Google Research. He co-authored influential projects like PoseNet and BodyPix and contributed key enhancements to TensorFlow.js models (notably BodyPix pixelation, ResNet support, and quantization options) that improved real-time segmentation performance for web deployment. His work spans applied research and product launches—publishing papers at CVPR, ECCV, and ICLR and shipping Google’s first Virtual Try-On for Shopping and cinematic features in Photos. Comfortable bridging research and cross-functional product teams, he has a track record of turning academic vision into scalable consumer features and pragmatic open-source engineering. An unexpected detail: he repeatedly blends motion-capture expertise from his NYU Movement Lab roots into modern web and mobile ML experiences.
10 years of coding experience
11 years of employment as a software developer
Master of Science (M.S.) Computer Science, Master of Science (M.S.) Computer Science at New York UniversityBachelor of Science (B.S.) Applied Mathematics, Bachelor of Science (B.S.) Applied Mathematics at Fudan UniversityShanghai High School
Github Skills (6)
tensorflowjs10
computer-vision10
machine-learning10
javascript10
model-optimization9
resnet9
Programming languages (3)
Github contributions (5)
tensorflow/tfjs-models
Jan 2019 - Nov 2019
Pretrained models for TensorFlow.js
Role in this project:
ML Engineer
ML EngineerContributions:28 commits, 39 PRs, 11 pushes in 9 months
Contributions summary:Tyler primarily focused on enhancing the BodyPix model within the TensorFlow.js ecosystem. They implemented new features like a pixelation rendering function and ResNet support for improved segmentation. The user also made significant contributions to refactoring and optimizing the demo interfaces, and added options for quantization to improve model performance. These changes collectively improved model performance and user experience.
javascriptmachine-learningpretrained-modelstensorflowtensorflow-js
tylerzhu-github/tfjs-models
Jan 2019 - Nov 2019
Pretrained models for TensorFlow.js
Contributions:194 pushes, 33 branches, 6 comments in 9 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.