Wenbing Li
Principal Software Engineer Technical Lead at Microsoft
California, United States
Summary
🤩
Rockstar🎓
Top SchoolWenbing Li is a Principal Software Engineer and Technical Lead based in California with over 15 years of software development experience and a focused eight-year run in senior roles driving AI and speech initiatives. At Microsoft he leads AI framework work and previously ran speech and Bing-related projects in Beijing and at Alibaba, blending product-driven engineering with research-grade techniques. He contributes to high-profile open-source ML tooling—helping improve model conversions and CI for ONNX, scikit-onnx, and ONNX Runtime—bringing practical expertise in model compatibility and cross-platform inference. Wenbing pairs deep domain knowledge in speech and AI frameworks with hands-on MLOps and automation work, notably adding iOS/Apple Silicon test pipelines and slimming runtime builds. Known for cleaning up complex model-conversion test suites and refactoring core conversion logic, he focuses on maintainability and reliable production deployment. He holds a master’s in Computer Software Engineering from the University of Science and Technology of China.
7 years of coding experience
7 years of employment as a software developer
Master's degree Computer Software Engineering, Master's degree Computer Software Engineering at University of Science and Technology of China
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (18)
ios10
python10
scikit10
testing10
machine-learning10
onnx10
ml10
mle10
keras10
xcode10
ci-cd-pipeline10
build-automation10
scikit-learn10
package-management9
github-ci9
Programming languages (4)
Github contributions (5)
onnx/onnxmltools
May 2018 - Nov 2020
ONNXMLTools enables conversion of models to ONNX
Role in this project:
ML Engineer
ML EngineerContributions:9 releases, 19 reviews, 71 commits in 2 years 5 months
Contributions summary:Wenbing primarily focused on cleaning up and improving Keras 2 Model API warnings within the testing framework. They modified multiple test files, specifically targeting end-to-end tests related to Keras model conversion to CoreML and ONNX. The changes primarily involved updating model definitions and compilation steps within the tests, demonstrating their focus on ensuring the accuracy and compatibility of Keras models during the conversion process.
python-librarypytorchdeep-learningmachine-learningonnx
onnx/sklearn-onnx
Dec 2018 - Aug 2019
Convert scikit-learn models and pipelines to ONNX
Role in this project:ML Engineer
ML EngineerContributions:2 releases, 43 reviews, 23 commits in 8 months
Contributions summary:Wenbing primarily contributed to restructuring and refactoring the `scikit-onnx` codebase. They made changes to various files, including core modules for conversion, shape calculation, and operator converters. Their commits involved updating dependencies, fixing build issues, removing unnecessary test data, and upgrading the package version. These activities suggest a focus on improving the library's functionality, maintainability, and release process within the context of converting scikit-learn models to ONNX.
pythondata-scienceonnxmachine-learningscikit-learn
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.