Zhenhua Wang
Senior Architect at NVIDIA
Shanghai, Shanghai, China
Summary
👤
Senior🎓
Top SchoolZhenhua Wang is a senior architect based in Shanghai with 11 years of experience building high-performance deep learning systems, virtual machines, and compute architectures. Currently driving R&D for NVIDIA TensorRT, he brings production-grade expertise in model optimization and deployment from prior engineering roles at Alibaba, Intel, and leading AI chip startup Cambrian. An active open-source contributor, he has made practical enhancements to the widely used ONNX project—improving model extraction, external data handling, and toolchain documentation to ease interoperability. Zhenhua pairs a strong academic foundation (MS from University of Chinese Academy of Sciences) with hands-on systems work, and is known for pragmatic solutions that bridge model-level research and low-level runtime efficiency.
11 years of coding experience
4 years of employment as a software developer
Master of Science - MS, Master of Science - MS at University of Chinese Academy of SciencesBachelor of Science - BS, Bachelor of Science - BS at Southeast University
English, Chinese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (7)
machine-learning10
onnx10
python10
deep-learning9
documentation8
tensorflow7
pytorch7
Programming languages (12)
Github contributions (5)
onnx/onnx
Oct 2020 - Sep 2021
Open standard for machine learning interoperability
Role in this project:
ML Engineer
ML EngineerContributions:11 reviews, 3 commits, 7 PRs in 10 months
Contributions summary:Zhenhua primarily contributes to the `onnx/onnx` repository, a project focused on machine learning interoperability, by implementing and refining utility functions for model extraction. Their work includes adding a function to extract parts of an ONNX model, fixing documentation, and enhancing the model extraction process, adding features to run model checkers optionally. They have also addressed issues related to external data handling and documentation updates for specific operators.
pytorchmxnetdeep-learninginteroperabilitymachine-learning
zhenhuaw-me/tensorflow
Nov 2018 - Nov 2019
TensorFlow 1.14 fork with Quantization Enhanced!
Contributions:6 PRs, 35 pushes, 40 branches in 1 year
quantizationmachine-learningtensorflow
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.