Henry Tao
Senior Machine Learning Engineer at Apple
United States
Summary
🤩
Rockstar🎓
Top SchoolHenry Tao is a Senior Machine Learning Engineer with six years of experience building production-ready ML pipelines and model tooling at Apple, backed by an MS from Carnegie Mellon and a BS in Electrical Engineering from National Taiwan University. He specializes in taking PyTorch models to production, improving robustness through rigorous error handling and type validation across recommender and object-detection stacks. An active open-source contributor to prominent projects like apple/turicreate and coremltools, he has strengthened model conversion, preprocessing checks, and evaluation workflows used by many ML practitioners. His background blends academic research in language technologies and multimedia with practical systems work, and he even paused for military service — a detail that reflects discipline and adaptability.
6 years of coding experience
7 years of employment as a software developer
Bachelor of Science - BS, Electrical Engineering, Bachelor of Science - BS, Electrical Engineering at National Taiwan UniversityMaster of Science - MS, Computer Science - Language Technologies, Master of Science - MS, Computer Science - Language Technologies at Carnegie Mellon University
English, Chinese
Github Skills (16)
error-handling10
machine-learning10
model-conversion10
tensorflow10
python10
recommender-system9
test-automation9
unit-testing9
object-detection9
pytorch9
deep-learning8
deeplearning-ai8
data-structures8
data-structure8
cprogramming-language7
Programming languages (3)
Github contributions (5)
apple/coremltools
Feb 2020 - Nov 2022
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 374 reviews, 55 commits in 2 years 9 months
Contributions summary:Henry primarily focused on improving error handling and testing within the Core ML tools repository. They implemented error handling for invalid image preprocessing parameters and added corresponding test cases. Furthermore, the user addressed typos and modified existing test cases related to reshape operations, particularly for GPU execution, including batch size limits. The user also contributed to unit tests for TensorFlow 2.x, adding examples and addressing type-checking issues, including tensor contraction.
pytorchmodel-conversionvalidationdeep-learningmachine-learning
apple/turicreate
Sep 2019 - Jan 2020
Turi Create simplifies the development of custom machine learning models.
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:1 release, 62 commits, 145 PRs in 4 months
Contributions summary:Henry primarily contributed to the back-end of the `turicreate` repository, specifically focusing on enhancing error handling and data type validation within the recommender and object detection toolkits. The user implemented robust type checking for input data in several recommender models (Ranking Factorization, Factorization, Item Similarity, and Popularity Recommenders). Further, the user addressed incorrect bounding box scales and refined model evaluation procedures. The user also worked on improving the efficiency of the SFrame sample function.
pythondeep-learningmachine-learningcoremlmulticlass-classification
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.