Weisu Yin
Machine Learning Engineer at Boson AI
Davis, California, United States
Summary
🤩
Rockstar🎓
Top SchoolWeisu Yin is a machine learning engineer with eight years’ experience building ML infrastructure and production systems, currently at Boson.ai. He previously worked on AWS Deep Engine-Science (Mu Li’s team), contributing to high-profile open-source projects AutoGluon and GluonCV—improving core fitting workflows, refactoring Ray-based parallelism, maintaining CI/CD, and converting model-zoo tables to CSV while adding PyTorch tutorials to boost usability. His profile spans backend and DevOps work as well as mobile and security-focused research: at UC Davis he developed gyroscope-based fraud detection and device-fingerprinting experiments, and earlier migrated an iOS CES demo from MVC to VIPER for maintainability. He holds an MS and BS in Computer Science from UC Davis and is known for pairing practical engineering with strong attention to developer experience.
8 years of coding experience
4 years of employment as a software developer
University of California, Davis
Chinese, English
Github Skills (18)
python10
mxnet10
deep-learning10
ci-cd10
computer-vision10
ray10
deep-learning-ai10
dockerce9
dockers9
ensemble-learning9
machine-learning9
docker9
documentations9
aws9
documentation9
Programming languages (9)
Github contributions (5)
autogluon/autogluon
Aug 2021 - Jan 2023
Fast and Accurate ML in 3 Lines of Code
Role in this project:
Back-end & DevOps Engineer
Back-end & DevOps EngineerContributions:3 releases, 518 reviews, 131 commits in 1 year 5 months
Contributions summary:Weisu's contributions primarily involved improving the codebase and supporting the project's infrastructure. They fixed fitting processes within the core, updated the code to support newer python versions, and refactored code related to parallel processing using Ray. The user also maintained the CI/CD pipeline by adding and adjusting build triggers.
forecastingimage-textmlppythonmeta-learning
dmlc/gluon-cv
Sep 2020 - Jun 2022
Gluon CV Toolkit
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:12 reviews, 29 commits, 40 PRs in 1 year 9 months
Contributions summary:Weisu refactored existing code related to model zoo documentation by converting tables into a CSV format for improved readability and organization. They also added features for auto-resizing tables and updated column width ratios within the documentation. Additionally, the user made contributions to add PyTorch tutorials to the existing documentation, demonstrating a focus on expanding the project's support for the PyTorch framework. Furthermore, the user added support for AWS Batch and Docker to the project.
pytorchmxnetperson-reidsemantic-segmentationdeep-learning
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.