Hyesoo Yang
Senior Software Engineer at Google
Mountain View, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHyesoo Yang is a Senior Software Engineer at Google with seven years of experience building ML infrastructure, cloud TPU systems, and rapid prototypes across Google Cloud, Firebase, and Google Brain. She specializes in efficient embedding computations and TPU integration—her open-source contributions to TensorFlow include TPU sparse-core support, minibatch processing, COO tensor conversion, and MLIR integration. Comfortable spanning low-level C++ libraries to high-level ML APIs, she combines research-oriented problem solving from an MIT Media Lab MS with pragmatic production delivery at scale. Based in Mountain View, she brings a rare mix of hardware-aware prototyping background (Daydream VR, Nest integration) and cloud ML engineering that accelerates both model performance and developer workflows.
7 years of coding experience
4 years of employment as a software developer
Master of Science (MS), MIT Media Lab, Master of Science (MS), MIT Media Lab at Massachusetts Institute of TechnologyBachelor's degree, Media Arts and Sciences, Bachelor's degree, Media Arts and Sciences at Wellesley College
Stackoverflow
1reputation
32reached
0answers
1question
Github Skills (10)
machine-learning10
tensorflow10
tpu10
python9
xla9
deep-learning8
c-language8
cprogramming-language8
mlops7
google-compute-engine6
Programming languages (5)
Github contributions (5)
tensorflow/tensorflow
May 2019 - Jun 2021
An Open Source Machine Learning Framework for Everyone
Role in this project:
ML Engineer
ML EngineerContributions:11 reviews, 190 commits, 2 PRs in 2 years 1 month
Contributions summary:Hyesoo contributed to the development of TPU-related components within the TensorFlow repository, with a focus on the sparse core accelerator. Their work included open-sourcing code for processing minibatches, adding statistics handling, and implementing functionality for converting tensors to COO format. The user also integrated a highway C++ library and contributed to the MLIR integration of sparse core operations. Their contributions support efficient embedding computations on TPUs.
pythondata-sciencedeep-learningmlmachine-learning
hyeygit/vllm
Mar 2025 - Apr 2025
A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:2 PRs, 23 pushes, 4 branches in 13 days
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.