Jim Wu
Member Of Technical Staff at OpenAI
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolJim Wu is a machine learning-focused software engineer with eight years of experience building high-performance ML infrastructure and model serving systems across leading AI companies. He has worked on efficient LLM inference, speculative decoding, sparsity, CUDA kernel optimizations, and video ML, with internships and full-time roles at Databricks Mosaic Research, Tesla Autopilot, Cohere, Genmo, and now OpenAI. Jim’s background blends systems engineering and applied research—shipping low-precision training pipelines at scale and production-grade serving stacks for large neural nets. Trained at the University of Waterloo and active in the San Francisco AI ecosystem, he favors practical optimizations that unlock order-of-magnitude gains in inference and training cost. A detail that sets him apart is his track record of moving research ideas into production, from Dojo-style training efficiency work to speculative decoding for faster LLM responses.
8 years of coding experience
3 years of employment as a software developer
Marc Garneau Collegiate InstituteBachelor of Computer Science, Computer Science, Bachelor of Computer Science, Computer Science at University of Waterloo
Github Skills (40)
python10
machine-learning10
api10
sdk10
gpu10
deep-learning10
compression10
pytorch9
numpy9
npm-package9
inference9
mixture-of-experts9
tensorflow9
ethereum9
neural-network9
Programming languages (7)
Github contributions (5)
jimwu6/RobotDrawer
Feb 2019 - Jun 2020
Contributions:5 commits, 4 pushes, 1 branch in 1 year 4 months
the-reckoner/reckoner-site
Mar 2018 - May 2021
Features, bug fixes, and tests for thereckoner.ca
Contributions:1 PR, 5 pushes, 3 issues in 3 years 2 months
testingfixes
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.