Peiyuan Liao
Founding Member Of Technical Staff at Project Prometheus
United States
Summary
🤩
Rockstar🎓
Top SchoolPeiyuan Liao is a Member of Technical Staff and machine learning engineer with seven years of experience bridging research systems and product engineering. He contributed to CMU Catalyst projects like GraphPipe and Collage that were integrated into TVM v0.9.0, and today builds video–language–action agents at General Agents while consulting for Terroir and Condé Nast. A Kaggle Competitions Grandmaster and former CTO who scaled a consumer-electronics team from 1 to 50+, he combines competitive modeling chops with product delivery and team growth. He is also an active open-source contributor—improving PyTorch clustering extensions through bug fixes, style cleanups, and test automation—evidence of a pragmatic, quality-first approach to ML infrastructure.
8 years of coding experience
6 years of employment as a software developer
Bachelor of Science Computer Science, Bachelor of Science Computer Science at Carnegie Mellon UniversityHigh School, Mathematics and Computer Science, High School, Mathematics and Computer Science at Kent School
Chinese, English, French
Github Skills (7)
pytorch10
python10
testing10
graph-neural-network9
geometric-deep-learning9
c-language8
c-programming-language8
Programming languages (13)
Github contributions (5)
rusty1s/pytorch_cluster
May 2020 - Jun 2020
PyTorch Extension Library of Optimized Graph Cluster Algorithms
Role in this project:
Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:17 commits, 1 PR, 22 comments in 1 month
Contributions summary:Peiyuan contributed to the project by fixing various errors and improving the code quality, specifically addressing Flake8 style issues to ensure code consistency. Their work involved modifying Python files, particularly within the `torch_cluster` directory. The user also implemented and updated several tests to validate the functionality of the implemented algorithms, ensuring correctness across various dimensions and configurations.
pytorchgeometric-deep-learningcluster-algorithmsmachine-learninggraph-neural-networks
liaopeiyuan/GAL
Sep 2020 - Jul 2021
Graph Adversarial Networks: Protecting Information against Adversarial Attacks
Contributions:1 review, 9 commits, 1 PR in 9 months
pytorchadversarial-attackssocial-network-analysisdataminingdeep-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.