Quan Gan
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolQuan Gan is a research-driven applied scientist with 12 years of experience bridging deep learning research and production systems, currently working on relational data modeling and large language models at HKU Shanghai Cross Innovation Lab and AWS. He combines a strong background in systems engineering and backend design with hands-on ML implementation—contributing to DGL (a prominent graph deep learning library) by implementing GNN modules such as a TreeGlimpsedClassifier. His experience spans industry roles at PepsiCo and AWS as well as academic research and teaching at NYU, giving him a rare mix of applied R&D and production delivery. Based in Shanghai, he leverages AWS and PyTorch expertise to move graph and language models from prototype to scalable deployment.
12 years of coding experience
2 years of employment as a software developer
New York UniversityBachelor's degree, Computer Science, Bachelor's degree, Computer Science at Fudan University
Github Skills (8)
neural-network10
graph10
pytorch10
deep-learning10
graph-neural-network10
graph-database10
graph-datastructures10
machine-learning9
Programming languages (10)
Github contributions (5)
dmlc/dgl
May 2018 - Jan 2023
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Role in this project:
ML Engineer
ML EngineerContributions:22 releases, 827 reviews, 487 commits in 4 years 9 months
Contributions summary:Quan contributed to the deep learning on graph library, DGL. The commits indicate the implementation of a GNN module, particularly a TreeGlimpsedClassifier based on a balanced tree of latent variables. Code changes involve modifications to model definition (model.py) and graph data structure (graph.py) as well as applying edge softmax. The user demonstrates an understanding of graph neural networks and their implementations as well as the use of PyTorch.
pytorchpythondeep-learningmachine-learninggraph-neural-networks
dglai/WWW20-Hands-on-Tutorial
Nov 2019 - Nov 2020
Contributions:15 commits, 12 pushes in 11 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.