Haoliang Zhang
Staff Software Engineer at Waymo
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHaoliang Zhang is a Staff Software Engineer with 11 years of experience building high-performance on-device and cloud ML infrastructure, currently enabling ML models to run efficiently at Waymo. Previously at Google he specialized in on-device AI, contributing significant runtime and TensorFlow Lite improvements—adding interpreter flags, delegate clustering control, and robust kernel implementations for widely used projects like tensorflow/tensorflow and tensorflow/runtime. His background spans production map-data systems at Baidu and AI research at Microsoft Research Asia, grounded in MS Computer Science from Yale and a BS in Applied Mathematics. Known for backend and runtime optimizations, he brings a rare combination of low-level kernel work and system-level productization that improves memory efficiency and execution stability. Based in Mountain View, he is currently not seeking opportunities but remains an active contributor to foundational open-source ML tooling.
11 years of coding experience
Bachelor of Science (B.S.) Applied Mathematics, Bachelor of Science (B.S.) Applied Mathematics at Beihang UniversityMaster of Science (M.S.) Computer Science, Master of Science (M.S.) Computer Science at Yale UniversityComputer Science, Computer Science at Chinese Academy of Sciences
English, Chinese
Github Skills (14)
kernel10
machine-learning10
tensorflow-lite10
c-language10
deep-learning10
tensorflow10
cprogramming-language10
mlr10
kernel-mode10
python9
deep-neural-networks9
neural-network9
memory-management9
integer-arithmetic8
Programming languages (3)
Github contributions (5)
tensorflow/tensorflow
Feb 2019 - Jan 2023
An Open Source Machine Learning Framework for Everyone
Role in this project:
ML Engineer
ML EngineerContributions:30 reviews, 288 commits, 8 PRs in 3 years 11 months
Contributions summary:Haoliang contributed to the TensorFlow Lite project, focusing on improving the functionality and stability of the library. Their commits included checking subgraph execution status and handling edge cases within the TensorFlow Lite framework. Furthermore, the user added features such as flags to python interpreter initializers, enabling control over delegate clustering and fixed kernels for the fill op.
pythondata-sciencedeep-learningmlmachine-learning
tensorflow/runtime
May 2020 - Apr 2021
A performant and modular runtime for TensorFlow
Role in this project:Back-end Developer
Back-end DeveloperContributions:12 commits in 11 months
Contributions summary:Haoliang made several contributions to the TensorFlow runtime project, focusing on kernel implementations and core functionality. They added new kernels for integer multiplication and implemented operations for TensorShape dialect, enhancing the runtime's capabilities. Furthermore, the user refactored and updated the code, optimizing memory allocation and introducing first-class definitions for tensor and host buffer types. These changes improved the efficiency and robustness of the runtime environment.
runtimeperformantmodulartensorflow
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.