Haojie Ye

Hardware Engineer at 温州长江汽车电子有限公司

Wenzhou, Zhejiang, China
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Haojie Ye is a hardware engineer with eight years’ experience in circuit design, PCB layout and EMC engineering, based in Wenzhou, China. Since 2015 he has driven ECC product development (SGM K256 and GM GEM) for global supply chains and currently leads production integration for Chery Jaguar Land Rover. He combines strong technical communication with hands-on design work, routinely bridging R&D and manufacturing to deliver automotive-grade electronics. Unusually for a hardware specialist, he has contributed to open-source adversarial ML tooling by improving Keras wrappers and attack implementations in the well-known cleverhans project, reflecting a broad curiosity across hardware and software domains.
code8 years of coding experience
book工学士, 电子信息工程, 工学士, 电子信息工程 at 杭州电子科技大学
languagesEnglish
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (8)

keras10
machine-learning10
adversarial-attacks10
tensorflow10
python10
security9
benchmarking6
benchmark6

Programming languages (5)

C++CScalaJupyter NotebookPython

Github contributions (5)

github-logo-circle
cleverhans-lab/cleverhans

Mar 2019 - Apr 2019

An adversarial example library for constructing attacks, building defenses, and benchmarking both
Role in this project:
userML Engineer
Contributions:12 commits, 2 PRs, 9 comments in 1 month
Contributions summary:Haojie primarily contributed to the `cleverhans-lab/cleverhans` repository by modifying the Keras wrapper and implementing and improving attacks. Their work involved adapting the Keras model wrapper to handle combined and stacked models. Additionally, the user fixed a bug in the untargeted LBFGS attack and implemented support for untargeted attacks by maximizing the true label loss, demonstrating experience in adversarial example generation. The user also refactored code to adhere to PEP8 standards.
benchmarkingrobustnessadversarial-machine-learningsecurityadversarial
HaojieYuan/autoAdv

Jun 2020 - Oct 2021

Contributions:2 releases, 116 commits, 2 PRs in 1 year 4 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.
Request Free Trial