Yijie Mei
Deep Learning Performance Architect at 英伟达公司
Minhang District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYijie Mei is a Deep Learning Performance Architect with 11 years of experience optimizing AI systems and compiler-driven model execution. Currently at NVIDIA after five years leading oneDNN Graph Compiler work at Intel, he specializes in auto-fusion, code generation, and performance tuning across OS, distributed systems, and programming languages. He holds advanced computer science degrees from Shanghai Jiao Tong University and the University of Melbourne, blending solid academic grounding with production-scale AI engineering. Based in Shanghai, Yijie pairs low-level systems insight with practical compiler techniques to squeeze out inference and training throughput, and his GitHub persona hints at a deep, almost poetic commitment to AI. Colleagues value him for turning research ideas into robust, high-performance implementations that ship in industry-grade toolchains.
11 years of coding experience
6 years of employment as a software developer
硕士学位, 计算机, 硕士学位, 计算机 at 上海交通大学硕士学位, Information technology, 硕士学位, Information technology at 澳大利亚墨尔本大学
Github Skills (97)
transformers10
apache-spark10
python10
metal10
sycl10
openmp10
deep-learning10
gpu10
ray10
cpp10
clang10
spirv10
tvm10
opencl10
javascript10
Programming languages (8)
Github contributions (5)
Menooker/Rootless
Sep 2020 - Jun 2022
chroot without ROOT!
Contributions:18 commits, 2 PRs, 15 pushes in 1 year 8 months
discordrootchroot
Menooker/quail
Feb 2018 - Mar 2019
Contributions:23 commits, 21 pushes, 1 branch in 1 year 1 month
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.