Shuyu Qin
Deep Learning Engineer at AT&T
New Jersey, United States
Summary
👤
Senior🎓
Top SchoolShuyu Qin is a Deep Learning Engineer and PhD candidate in Computer Science at Lehigh University with eight years of research and engineering experience building novel generative and representation models for scientific and networked data. Currently at AT&T, she develops Network Foundation Models for multimodal representation learning, translating advanced research into scalable models for complex network datasets. Her prior work includes a 20% improvement over state-of-the-art on 4D-STEM image domain mapping via a Cycle-Consistent-Spatial-Transforming Autoencoder and shipping pip-installable packages (Auto4DSTEM, Deep Matter) that package custom VAEs, transformers, and training utilities for reproducible science. She has built specialized architectures—custom transformers, LSTM-β-VAEs, and optimized loss functions—for denoising, domain transfer, and interpretable latent spaces across hyperspectral and microscopy data. Based in Bethlehem, PA, Shuyu blends deep theoretical understanding with practical software delivery, often turning supervised problems into unsupervised solutions to unlock new application avenues.
8 years of coding experience
6 years of employment as a software developer
Bachelor's degree Physics, Bachelor's degree Physics at Nanjing UniversityDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Lehigh UniversityMaster's degree Mechanical Engineering, Master's degree Mechanical Engineering at Washington University in St. Louis
Chinese, English
Github Skills (7)
autoencoder8
classification5
sequence-to-sequence4
multimodal3
automation3
neural-network2
machine-learning2
Programming languages (2)
Github contributions (5)
shuyuqin/497_MAT_Assignment
Sep 2019 - Nov 2021
Contributions:194 pushes, 1 branch in 2 years 2 months
shuyuqin/Faster-than-Faster-Better-than-Better-Machine-Learning-Electromechanical-Switching-in-Ferroelec
Nov 2020 - Oct 2021
fast and better machine learning method
Contributions:1 PR, 50 pushes, 1 branch in 11 months
machine-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.