Ziyao Li
Algorithm Engineer at WeRide
Haidian District, Beijing, China
Summary
🤩
Rockstar🎓
Top SchoolZiyao Li is an algorithm engineer and PhD from Peking University with eight years of experience applying graph machine learning to molecular and biomedical problems, and recent work in prediction, planning, and control for autonomous driving at WeRide. He combines deep expertise in GNNs, protein and drug modeling, and broad deep learning skills across CV and NLP, informed by research roles at DPTechnology and multiple industry internships including Microsoft Research Asia. Practically-minded, he has contributed backend and ML engineering improvements to the widely used deepmd-kit project, optimizing training/validation and data pipelines for molecular dynamics models. Prior quantitative research experience at Ubiquant and dual academic training in data science and the arts give him a rare mix of rigorous technical depth and interdisciplinary perspective.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD Data Science, Doctor of Philosophy - PhD Data Science at Peking University
English, Chinese
Github Skills (13)
data-handling10
machine-learning10
deep-learning10
trainings10
tensorflow10
python10
modeling10
nonlinear-dynamics9
molecular-dynamics-simulation9
molecular-simulation9
cprogramming-language5
c-language5
cuda5
Programming languages (5)
Github contributions (5)
deepmodeling/deepmd-kit
Apr 2021 - Apr 2021
A deep learning package for many-body potential energy representation and molecular dynamics
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:5 reviews, 18 commits, 3 PRs in 6 days
Contributions summary:Ziyao made significant contributions to the `deepmd-kit` repository, focusing on enhancing the training and validation processes. They implemented validation support and removed test-related code. They also made optimizations to data handling by altering data configuration schemes, optimizing the `get_batch` function, and modifying the way evaluation results are derived. These changes indicate a focus on improving the functionality and efficiency of the deep learning model training pipeline.
lammpspythonipideepmdtensorflow
dptech-corp/Uni-Fold-jax
Dec 2021 - Aug 2022
Contributions:20 commits, 5 PRs, 13 pushes in 8 months
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.