Chengji Yao

Staff Software Engineer at Google

Bellevue, Washington, United States
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

🤩
Rockstar
🎓
Top School
Chengji Yao is a Staff Software Engineer with 11 years of experience building large-scale AI infrastructure and compiler/runtime systems, now based in Bellevue, Washington. He has held senior engineering roles at Google and ByteDance, where he worked on LLM systems and contributed to ByteDance's ByteIR project, and earlier focused on AI frameworks at MEGVII and AI infrastructure at Microsoft. Chengji excels at bridging research and production, optimizing training and runtime performance for large sparse and dense models. He holds MS and BS degrees in Electronic Engineering from Tsinghua University and often operates at the intersection of compilers, runtime systems, and model engineering. Colleagues know him for tackling low-level performance bottlenecks while keeping an eye on developer ergonomics and deployability. Outside obvious product work, he has a track record of contributing to open-source AI tooling that accelerates model delivery into production.
code11 years of coding experience
job9 years of employment as a software developer
bookMaster of Science (MS) Electronic Engineering, Master of Science (MS) Electronic Engineering at Tsinghua University
languagesChinese, English
github-logo-circle

Github Skills (89)

dep10
dataflow10
python10
mxnet10
metal10
mlops10
deep-learning10
gpu10
serverless10
gpu-acceleration10
clang10
portable10
opencl10
javascript10
modular10

Programming languages (6)

C++CLLVMGoMLIRPython

Github contributions (5)

github-logo-circle
yaochengji/pytorch

May 2020 - Jul 2024

Tensors and Dynamic neural networks in Python with strong GPU acceleration
Contributions:52 pushes, 5 branches in 4 years 2 months
pythongpu-accelerationdeep-learninggpuacceleration
yaochengji/vllm

Feb 2025 - Apr 2025

A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:5 reviews, 7 PRs, 70 pushes in 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.
Request Free Trial