Linbin Yu
Research Scientist at Facebook
Menlo Park, California, United States
Summary
🤩
Rockstar🎓
Top SchoolLinbin Yu is a research scientist with six years of experience building and deploying machine learning models and mobile infrastructure at Facebook, focused on optimizing latency and binary size for on-device vision, NLP, and ranking systems. He has production mobile engineering roots from Zynga and a strong academic background culminating in a PhD in Computer Science and Engineering. Linbin led a team to build an automatic parameter tuning system using Facebook's Ax and has driven Android performance logging and analysis efforts, blending research rigor with product-grade engineering. As an active contributor to the PyTorch ecosystem, he improved its build and test infrastructure—work that helped streamline mobile test workflows and integration of XNNPACK/QNNPACK. Colleagues would describe him as a pragmatic scientist who turns infrastructure-level improvements into measurable gains for mobile ML deployment.
6 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy (PhD), Computer Science and Engineering, 3.9/4.0, Doctor of Philosophy (PhD), Computer Science and Engineering, 3.9/4.0 at The University of Texas at ArlingtonB.S, Electronic Science and Technology, B.S, Electronic Science and Technology at University of Science and Technology of China
Stackoverflow
11reputation
0reached
1answer
0questions
Github Skills (16)
xpack10
python10
build-automation10
cicd9
autograd9
gpu9
cprogramming-language9
neural-network9
machine-learning9
c-language9
deep-learning9
tensor9
testing8
apache-spark6
hive6
Programming languages (2)
Github contributions (5)
pytorch/pytorch
Sep 2019 - Sep 2022
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
Back-end Developer
Back-end DeveloperContributions:34 reviews, 298 commits, 131 PRs in 3 years
Contributions summary:Linbin primarily focused on improving the build process and test infrastructure for the PyTorch project. Their contributions include moving XNNPACK and QNNPACK to shared BUCK build files, consolidating python targets, and modifying configuration files. Additionally, the user addressed a missing operator error message and added instructions for iOS tests. These modifications enhanced the project's build system and testing capabilities.
pythongpu-accelerationdeep-learninggpunumpy
linbinyu/pytorch
Aug 2019 - Oct 2022
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Contributions:2 PRs, 197 pushes, 69 branches in 3 years 2 months
pythongpu-accelerationdeep-learninggpuacceleration
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.