Henry Tu
Incoming Member Of Technical Staff at Cerebras Systems
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHenry Tu is a software engineer with nine years of hands-on experience building ML frameworks, full-stack systems, and hardware-integrated robotics projects, currently joining Cerebras Systems as a Member of Technical Staff. He has delivered production-grade AWS services at Amazon, architected scalable web platforms at the University of Toronto and Hack the 6ix, and led a 27-person organizer team to run an international hackathon. At Cerebras and via the LLVM Foundation he contributed 37+ upstream commits to Torch-MLIR and PyTorch—creating a Lazy Tensor Core frontend that helps link PyTorch to MLIR and accelerate support for new hardware. Henry combines low-level compiler and backend work with practical front-end and cloud skills, and enjoys applying that full-stack lens to IoT and robotics projects involving Raspberry Pi and 3D printing. Based in San Francisco, he pairs strong academic performance from the University of Toronto with a track record of making complex ML systems debuggable and production-ready.
9 years of coding experience
3 years of employment as a software developer
Ontario Secondary School Diploma, Ontario Secondary School Diploma at Vincent Massey Secondary SchoolHonours Bachelor of Science - HBSc, Computer Science, 3.95/4.0 cGPA, Honours Bachelor of Science - HBSc, Computer Science, 3.95/4.0 cGPA at University of Toronto
Stackoverflow
1reputation
173reached
0answers
1question
Github Skills (14)
pytorch10
backend10
back-end-development10
python10
mlr10
compiler-compiler9
compiler9
c-language8
cprogramming-language8
powerbi6
spotfire6
tableau-api6
shapefile6
geospatial6
Programming languages (11)
Github contributions (5)
llvm/torch-mlir
Feb 2022 - Aug 2022
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:29 reviews, 45 commits, 75 PRs in 6 months
Contributions summary:Henry primarily contributed to enhancing the Torch-MLIR project's ability to import and handle PyTorch models. Their work involved adding support for various operations such as `prim::Constant` with list types, and also for native batch normalization and other backward operations. The user's contributions specifically involved modifying and extending the functionality of importers and related files to correctly handle and translate PyTorch operations within the MLIR framework. They also made changes to the backend setup for testing.
pytorchcompilermlir
RASTERA/HUBG-Client
Apr 2018 - Dec 2020
Contributions:130 commits, 1 push in 2 years 9 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.