Xiaoyu Zhang
Software Engineer at Microsoft
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolXiaoyu Zhang is a software engineer based in Seattle with five years of experience building performance-oriented systems at Microsoft after internships at Google and Salesforce. At Microsoft they contributed to ONNX Runtime—one of the flagship open-source ML inference projects—by adding ModelProto support to accelerate model optimization and quantization while eliminating disk I/O and fixing related external-data bugs. Comfortable in both research-adjacent and production settings, Xiaoyu has a master's from Northeastern and has served as a teaching assistant there, signaling strong communication and mentorship skills. Their GitHub persona hints at a playful curiosity, and their work reflects a focus on practical engineering improvements that yield measurable runtime and developer-experience gains.
4 years of coding experience
1 year of employment as a software developer
Master's degree, Master's degree at Northeastern University
Chinese, English, Japanese
Github Skills (10)
transformers10
machine-learning10
deep-learning10
onnx10
onnxruntime10
python10
model-optimization9
ai-framework9
quantization9
pytorch8
Programming languages (6)
Github contributions (5)
microsoft/onnxruntime
May 2023 - Jan 2025
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
ML Engineer
ML EngineerContributions:20 reviews, 6 PRs, 3 pushes in 1 year 8 months
Contributions summary:Xiaoyu contributed to the ONNX Runtime by adding support for `ModelProto` as input to several APIs, enabling faster model optimization and quantization by avoiding disk I/O. They modified existing functionalities to accommodate `ModelProto` input, specifically within the transformers optimizer and quantization tools. Furthermore, the user addressed a bug related to handling `ModelProto` in the quantization process, ensuring the integrity of external data.
runtimetrainingtensorflowai-frameworkaccelerator
xiaoyu-work/onnxruntime
Mar 2024 - Jan 2025
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Contributions:23 pushes, 2 branches in 9 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.