Shang-yun Wu
Machine Learning Engineer at Apple
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolShang-yun Wu is a Machine Learning Engineer with eight years of experience building research-driven software and robotics systems, currently contributing to ML work at Apple after prior engineering roles at Microsoft and MIT CSAIL. Trained at MIT (BS and MEng in EECS), he blends academic research—co-authoring papers in high-profile venues and working in Media Lab and Koch Institute labs—with production engineering across Amazon Robotics and Applied Predictive Technologies. He contributes to open-source interpretability tooling, improving the popular SHAP library and its benchmarking for MaskedModel evaluations, signaling a focus on model explainability and robust testing. Known for fast learning and cross-disciplinary problem solving, he brings a rare mix of hardware-aware robotics experience, medical-engineering research, and practical ML product development.
8 years of coding experience
6 years of employment as a software developer
Bachelor's degree, Electrical Engineering and Computer Science, Bachelor's degree, Electrical Engineering and Computer Science at Massachusetts Institute of Technology
English, Chinese, Chinese, Japanese
Github Skills (11)
machine-learning10
deeplearning-ai10
explainable-artificial-intelligence10
deep-learning10
shap10
python10
testing9
numpy8
scikit7
scikit-learn7
gradient-boosting5
Programming languages (2)
Github contributions (5)
shap/shap
Dec 2020 - Jan 2021
A game theoretic approach to explain the output of any machine learning model.
Role in this project:
ML Engineer
ML EngineerContributions:33 reviews, 11 commits, 11 PRs in 1 month
Contributions summary:Shang-yun contributed to the SHAP library, a project focused on explaining machine learning model outputs. Their work involved modifying the `_explanation.py` and `setup.py` files, likely related to the handling and presentation of explanations. Furthermore, they adapted a benchmarking framework to support MaskedModel, demonstrating a focus on evaluating and improving the interpretability of models. The commits also involved adding and fixing tests for the benchmark framework and perturbation tests.
explaininterpretabilityshapdeep-learningapproach
maggiewu19/shap
Sep 2020 - Jan 2021
A game theoretic approach to explain the output of any machine learning model.
Contributions:14 PRs, 45 pushes, 7 branches in 4 months
approachexplainmachine-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.