Chenguang Wang
Software Engineer at Google
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolChenguang Wang is a software engineer in Seattle with 14 years of experience specializing in compilers and machine learning compilation. At Google he builds ML compilers for Edge TPU and has a strong track record improving MLIR/StableHLO and XLA optimizations for real-world workloads like concatenations, reshapes, dot products, and fp16/bf16 constant folding. His open-source contributions span TensorFlow, XLA, and LLVM—where he’s improved compiler transformations, TF-to-StableHLO conversions, and Bazel build reliability—showing both deep compiler expertise and practical build/release automation skills. Earlier work includes designing a language interpreter and advanced features for Twitter’s anti-spam rule engine, demonstrating a taste for language design and asynchronous systems. Colleagues describe him as a “compiler enthusiast” who prefers roles tightly focused on compilation challenges and optimization at the intersection of ML and systems.
14 years of coding experience
7 years of employment as a software developer
University of Washington
English, Chinese, Japanese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (19)
c-language10
stable10
llvm10
machine-learning10
build-system10
mlr10
constant-folding10
automation10
deep-learning10
tensorflow10
bazel10
compiler-optimization10
automations10
cprogramming-language10
float329
Programming languages (10)
Github contributions (5)
llvm/llvm-project
Mar 2023 - Aug 2024
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:
Automation Engineer / Build & Release Engineer
Automation Engineer / Build & Release EngineerContributions:18 PRs, 12 pushes, 4 comments in 1 year 5 months
Contributions summary:Chenguang primarily focused on improving the build process within the LLVM project, particularly related to Bazel builds. They added missing dependencies, fixed build breakages, and adjusted configuration files to ensure the build system functioned correctly. Their contributions included addressing issues in MLIR and LLVM components and resolving dependency issues in the Bazel build system. They also reverted one of their commits.
compilerstechnologiesclangsubmittoolchain
tensorflow/tensorflow
Aug 2021 - Jan 2023
An Open Source Machine Learning Framework for Everyone
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:24 commits, 3 PRs, 3 comments in 1 year 5 months
Contributions summary:Chenguang's contributions focused on optimizing the StableHLO compiler within the TensorFlow framework. They implemented and refined code transformations to improve performance, specifically related to concatenations, reshaping operations, and dot product operations. Their work involved modifying the MLIR compiler infrastructure to support and optimize these operations. Furthermore, they addressed errors in TF-to-StableHLO conversions, highlighting their involvement in the integration and optimization of the machine learning compilation pipeline.
pythondata-sciencedeep-learningmlmachine-learning
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.