Aobo Yang
Software Engineer at Meta
Hong Kong Island, Hong Kong, United States
Summary
🤩
Rockstar🎓
Top SchoolAobo Yang is a software engineer with 11 years of cross-industry experience spanning fintech, academia, government, enterprise and startups, currently at Meta after earning an MS in Computer Science from the University of Virginia. He continues research on explainable recommendation systems as a UVA research assistant, blending applied ML research with production engineering. His background includes leading engineering at AfterShip and hands-on work in frontend, backend, cloud infrastructure and MLOps. An active open-source contributor, he improved progress reporting and tutorials for feature-attribution methods in the popular PyTorch Captum project, reflecting a practical focus on model interpretability. Comfortable moving between research and production, he brings a rare combination of academic rigor and long-term commercial delivery across diverse technical stacks.
11 years of coding experience
6 years of employment as a software developer
Bachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at Hong Kong Baptist UniversityMaster of Science - MS Computer Science, Master of Science - MS Computer Science at University of Virginia
Chinese, English
Stackoverflow
157reputation
9kreached
3answers
7questions
Github Skills (16)
pytorch10
machine-learning10
interpretation10
python10
unit-testing9
tqdm8
devops7
aix6
cursor6
datetime6
html6
ajax6
db26
javascript6
dynamic-sql6
Programming languages (7)
Github contributions (5)
pytorch/captum
Mar 2021 - Jan 2023
Model interpretability and understanding for PyTorch
Role in this project:
Backend Developer & MLOps Engineer
Backend Developer & MLOps EngineerContributions:4 releases, 43 reviews, 57 commits in 1 year 10 months
Contributions summary:Aobo implemented and integrated progress reporting functionality for several feature attribution methods, including FeatureAblation, Shapley, and LIME-based methods. They added unit tests and addressed code formatting issues. Additionally, the user supported normalization within metric infidelity and updated existing tests for the "show_progress" feature. The user also added a tutorial for LIME and performed dependency updates and various code style improvements.
pytorchinterpretable-aifeature-importanceunderstandinginterpretability
aobo-y/aobo-y.github.io
Apr 2015 - May 2020
Contributions:26 pushes, 2 branches in 5 years 1 month
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.