Yanhua Huang
CMM Software Engineer at Hexagon Metrology
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYanhua Huang is a CMM software engineer based in Shanghai with 10 years of experience building integrated CAD/CAM/CMM systems centered on GD&T and the New GPS standard. At Hexagon Metrology she focuses on bridging precision metrology requirements with practical software solutions, drawing on earlier CAD engineering roles including SolidWorks integration and GD&T specification tooling. She has hands-on expertise in implementing measurement workflows and automating inspection chains, and she contributes to open-source ML tooling—adding reinforcement learning DQN variants and replay improvements to the well-known TensorLayer library. That blend of metrology domain depth and practical ML experimentation gives her a rare perspective on applying algorithmic techniques to real-world engineering problems. Trained to a master’s level in precision instruments and machinery, she pairs rigorous academic background with a pragmatic, product-oriented engineering approach.
10 years of coding experience
3 years of employment as a software developer
Master, Precision Instrument and Machinery, Master, Precision Instrument and Machinery at HUST
Github Skills (9)
tensorlayer10
dqn10
deep-learning10
tensorflow10
python10
reinforcement-learning10
ml9
machine-learning9
mle9
Programming languages (3)
Github contributions (5)
tensorlayer/TensorLayer
May 2019 - Sep 2019
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
Role in this project:
ML Engineer
ML EngineerContributions:19 commits, 1 PR, 17 pushes in 4 months
Contributions summary:Yanhua contributed to reinforcement learning tutorials within the tensorlayer repository. Their primary focus was on implementing and documenting various DQN (Deep Q-Network) variants, including Double DQN, Dueling DQN, and Noisy DQN, as well as the Retrace algorithm and Prioritized Experience Replay. The user's work involved creating and modifying code examples and integrating wrappers for Atari environments, which improved the library's reinforcement learning capabilities.
tensorflow-tutorialscientistspythongoogledeep-reinforcement-learning
deep-reinforcement-learning-book/Chapter4-DQN
Nov 2019 - Mar 2022
DQN examples codes in chapter 4
Contributions:1 review, 9 commits, 4 PRs in 2 years 4 months
chapterdqn
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.