Hyomin Choi
Senior Staff Engineer at InterDigital, Inc.
Los Altos, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHyomin Choi is a Senior Staff Engineer based in Los Altos with seven years of industry experience focused on compression and scalable video systems. She combines a strong academic foundation (PhD-level research) with hands-on engineering from firmware-level codec work at LG to modern ML-driven compression at InterDigital. Her open-source contributions include implementing the ScaleSpaceFlow network in the well-regarded CompressAI PyTorch library, translating research ideas into training-ready, end-to-end video compression code. Hyomin excels at bridging algorithmic research and production engineering, delivering encoder/decoder and hyperprior components that enable practical optimized codecs. Known for digging into both low-level decoder internals and deep learning model design, she brings rare full-stack expertise in multimedia compression.
7 years of coding experience
8 years of employment as a software developer
Master of Engineering, Computer Engineering, 4.5/4.5, Master of Engineering, Computer Engineering, 4.5/4.5 at Kwangwoon UniversityDoctor of Philosophy - PhD, Engineering Science, Doctor of Philosophy - PhD, Engineering Science at Simon Fraser University
English, French, Korean
Github Skills (8)
neural-network10
compression10
pytorch10
machine-learning10
deep-learning10
deep-neural-networks10
python10
video-compression9
Programming languages (2)
Github contributions (5)
InterDigitalInc/CompressAI
Nov 2021 - Jan 2022
A PyTorch library and evaluation platform for end-to-end compression research
Role in this project:
ML Engineer
ML EngineerContributions:15 commits, 5 pushes, 2 branches in 1 month
Contributions summary:Hyomin's primary contribution involves the implementation and enhancement of the `ScaleSpaceFlow` network within the `compressai` library, focusing on end-to-end optimized video compression research. They added the `ScaleSpaceFlow` network, which includes encoder, decoder, and hyperprior components. Furthermore, the user worked on implementing compression and decompression functions and included example training code. This work demonstrates a focus on deep learning model development within the context of video compression.
pytorchpythonend-to-enddeep-learningcompression
chyomin06/ScalableImageCodingHumansMachines
Jun 2022 - Jun 2022
A learned image compression model originally proposed in Scalable Image Coding for Humans and Machines
Contributions:1 push in 1 day
scalableimage-optimizationmachineslearnedcompression
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.