Yifei Yang
Irvine, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYifei Yang is a pragmatic software engineer with 7 years of experience building full-stack systems and ranking infrastructure at Meta, where he led cross-org teams to ship comment and video deep-dive features that measurably improved Facebook DAU and watch time. He combines production experience across backend, ranking, and iOS with hands-on ML/vision contributions to prominent OpenMMLab projects—implementing StyleGAN inversion and training hooks while improving core data transforms and docs. Comfortable leading product design and tooling, he also created an internal ranking inspector used broadly across Facebook for debugging delivery context. Based in Irvine, he pairs high-impact engineering with a curiosity for generative models and a taste for the outdoors as an avid hiker and weekly golfer.
7 years of coding experience
4 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at Carnegie Mellon University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (21)
pytorch10
hook10
python10
apidoc10
image-processing10
diffusion-models10
configuration-management10
machine-learning10
stylegan10
generative-adversarial-network10
deep-learning10
trainings10
sd-mmc10
generative-model10
computer-vision10
Programming languages (2)
Github contributions (5)
open-mmlab/mmgeneration
Apr 2021 - Dec 2022
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Role in this project:
ML Engineer
ML EngineerContributions:7 releases, 186 reviews, 446 commits in 1 year 8 months
Contributions summary:Yifei implemented the initial version of an image inverting tool. This involved the creation of a Python application for inverting StyleGAN-based generators, indicating work in the generative modeling space. The commits show the integration of a perceptual loss and noise regularization within the project, and also involved creating an interpolation tool to interpolate the latent space in styleGAN models.
pytorchstylegangenerative-adversarial-networkmmcvgan
open-mmlab/mmagic
Jan 2021 - Jan 2023
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
Role in this project:Technical Writer
Technical WriterContributions:1 release, 200 reviews, 57 commits in 2 years
Contributions summary:Yifei primarily focused on refactoring and updating documentation files within the "docs" directory. Their commits demonstrate a focus on improving the structure, content, and formatting of the documentation, including updates to the table of contents and API references. They also corrected minor formatting issues to enhance readability. The user's work likely aims to improve the clarity and usability of the project's documentation for other users.
mattingimage-synthesistext-to-imagevideo-super-resolutionvideo-restoration
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.