Zhijiang Li
Senior Software Engineer at Microsoft
Suzhou City, Jiangsu, China
Summary
🤩
RockstarZhijiang Li is a Senior Software Engineer based in Suzhou with seven years of experience building Android applications and developer tooling at major technology companies including Microsoft and Tencent. At Microsoft he has advanced from EDGE Android work to leading Teams Android development and contributing to LLM evaluation systems, combining mobile client expertise with backend evaluation infrastructure. His open-source contributions to high-profile ML projects like ONNX Runtime and tensorflow-onnx show a pragmatic focus on build and deployment efficiency (Docker/CMake optimizations) and on enabling model interoperability through operator support and testing. Colleagues would describe him as the engineer who tightens CI/CD bottlenecks while also shipping production-quality Android features. He brings a mix of hands-on coding, DevOps sensibility, and a taste for improving developer experience across the ML and mobile stacks.
7 years of coding experience
7 years of employment as a software developer
Github Skills (17)
docker10
python10
data-export10
onnx10
dockers10
exporter10
cicd10
deep-learning10
tensorflow10
build-automation10
exports10
convert9
converting9
cmake9
keras9
Programming languages (4)
Github contributions (5)
onnx/tensorflow-onnx
Oct 2018 - Aug 2019
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
Role in this project:
Back-end Developer
Back-end DeveloperContributions:193 commits, 82 PRs, 26 pushes in 10 months
Contributions summary:Zhijiang contributed to the conversion of TensorFlow models to the ONNX format within the tensorflow-onnx repository. Their work included implementing support for new TensorFlow operators like Div, and enhancing existing ones by handling complex data types and adding necessary logic for specific scenarios, as well as addressing attribute errors related to batch matrix multiplication. Furthermore, the user refactored code according to feedback. Finally, the user added test support for operators GRU and GRUBlock.
tensorflowjsexportdeep-learningonnxkeras-tensorflow
microsoft/onnxruntime
Oct 2019 - Jan 2023
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:DevOps Engineer
DevOps EngineerContributions:97 reviews, 60 commits, 48 PRs in 3 years 3 months
Contributions summary:Zhijiang's commits primarily focus on optimizing the build and deployment process within the ONNX Runtime project. They made changes to the Dockerfile to improve image layer reuse, speed up the build process using parallel compilation, and merge steps to reduce image size. Furthermore, the user addressed a bug in the CMake configuration related to the server component. Their contributions demonstrate a focus on efficiency and streamlining the build and deployment infrastructure of the project, particularly related to the Docker build process.
runtimetrainingtensorflowai-frameworkaccelerator
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.