Jie An
Applied Scientist at Amazon
City of Rochester, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolJie An is an Applied Scientist at Amazon AGI with nine years of experience building and researching generative image and video models across top tech labs including Meta, Apple, and Microsoft. He holds a PhD candidacy at the University of Rochester and combines deep academic rigor with hands-on engineering—evident from contributions like a coarse-to-fine CNN and fast target-search algorithm for an AI WeChat Jump project. His work spans diffusion transformers, text-to-video generation, GANs, and visual-language interleaved generation, showing a consistent focus on pushing perceptual quality and controllability in generative systems. Based in Rochester, NY, Jie blends mathematical training from Peking University with practical research internships to move ideas from prototype to production-scale research in industry settings.
9 years of coding experience
1 year of employment as a software developer
Master of Applied Mathematics, Master of Applied Mathematics at Peking UniversityDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Rochester
Github Skills (8)
mask-rcnn10
faster-rcnn10
computer-vision10
machine-learning10
tensorflow10
python10
ai10
opencv9
Programming languages (3)
Github contributions (5)
Prinsphield/Wechat_AutoJump
Jan 2018 - Jan 2018
AI plays WeChat Jump Game
Role in this project:
ML Engineer
ML EngineerContributions:16 commits, 1 PR, 16 pushes in 7 days
Contributions summary:Jie focused on implementing and refining a machine learning model for the WeChat Jump Game. They modified the code to include a "fast" target position search algorithm, and introduced a coarse-to-fine convolutional neural network (CNN) model. The user also added the necessary configurations and code for training the CNN model. The commits demonstrate the user's involvement in improving the game's AI through neural network architectures.
aiwechat
pkuanjie/StyleNAS
Dec 2019 - Jul 2020
Official pytorch implementation of the paper: "Ultrafast Photorealistic Style Transfer via Neural Architecture Search"
Contributions:8 commits, 6 pushes, 1 branch in 7 months
neural-architecture-searchpytorchstyle-transfer
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.