Rui Y
Software Engineer at Microsoft
Sunnyvale, California, United States
Summary
🤩
Rockstar🎓
Top SchoolRui Y is a software engineer based in Sunnyvale with nine years of experience focused on AI frameworks and ML inferencing. At Microsoft since 2021, he contributes to high-performance tooling such as ONNX Runtime, shipping model-optimization fixes, training export fallbacks for OOM resilience, and fusion passes for multi-query attention. His background combines engineering masters from Carnegie Mellon and Tianjin University with a brief market-analyst stint, giving him both technical depth and product-context awareness. Rui’s open-source contributions to a widely used project like ONNX Runtime reflect a practical knack for making research-grade models more robust and production-ready.
9 years of coding experience
Master's degree, Engineering, Master's degree, Engineering at Carnegie Mellon University's College of EngineeringMaster of Science - MS, Technology Venture, Master of Science - MS, Technology Venture at Carnegie Mellon University - Integrated Innovation InstituteBachelor's degree, Engineering, Bachelor's degree, Engineering at Tianjin University
Chinese, English
Github Skills (11)
machine-learning10
onnx10
python10
model-optimization10
deepspeed9
pytorch9
neural-network8
hardware-acceleration8
artificial-neural-networks8
ai-framework7
tensorflow6
Programming languages (8)
Github contributions (5)
microsoft/onnxruntime
Oct 2022 - Jan 2023
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
ML Engineer
ML EngineerContributions:1 release, 19 reviews, 11 commits in 2 months
Contributions summary:Rui contributed to the ONNX Runtime project by addressing various issues related to model optimization and training. Their work includes bumping the ONNX Runtime version number, updating dependencies like DeepSpeed, and fixing fallback mechanisms within the ORTModule for handling potential out-of-memory (OOM) errors during ONNX model export. Furthermore, they added a fusion pass to optimize model graphs for multi-query attention and added a macro to help debug graphs.
machine-learningonnxruntimedeep-learningonnxneural-networks
rui-ren/The-optimized-vibration-frequency
Nov 2016 - Feb 2020
Contributions:7 commits, 9 pushes, 2 branches in 3 years 3 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.