Siyuan Liu
Member Of Technical Staff at OpenAI
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolSiyuan Liu is a Member of Technical Staff in the San Francisco Bay Area with a decade of experience building deep learning infrastructure and ML systems. He has driven performance engineering for vLLM on TPU and PyTorch/XLA as a Senior Software Engineer at Google, and previously developed neural network tooling and inference infrastructure at Ambarella. Trained as an electrical and computer engineer (MS, Duke) with a BE from Beijing University of Technology, he blends hardware-aware optimization with software engineering rigor. Siyuan’s trajectory shows a consistent focus on productionizing ML workloads across edge and cloud environments, from intern projects to large-scale TPU deployments. Colleagues know him for translating algorithmic needs into robust tooling and squeezing efficient execution from complex stacks. He is currently applying that expertise at OpenAI, continuing to bridge research models and production systems.
11 years of coding experience
7 years of employment as a software developer
Master of Science - MS Electrical and Computer Engineering, Master of Science - MS Electrical and Computer Engineering at Duke UniversityHigh School Diploma, High School Diploma at Beijing No.2 High SchoolBachelor of Engineering - BE Electrical and Information Engineering, Bachelor of Engineering - BE Electrical and Information Engineering at Beijing University of Technology
Chinese, English
Github Skills (58)
pytorch10
artificial-intelligence10
batching10
python10
llama10
machine-learning10
inference10
onnx10
tpu10
amd10
numpy10
llm10
ml10
keras10
deep-learning10
Programming languages (4)
Github contributions (5)
lsy323/xla
Jan 2023 - Mar 2023
Enabling PyTorch on Google TPU
Contributions:1 review, 33 commits, 1 PR in 2 months
pytorchtpu
lsy323/vllm
Jul 2024 - Aug 2025
A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:2 PRs, 162 pushes, 50 branches in 1 year
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.