Jihoon Lee

소프트웨어 엔지니어 at NAVER WEBTOON

Seoul, South Korea
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Jihoon Lee is a software engineer with 10 years of experience specializing in ML systems and MLOps, currently engineering machine-learning infrastructure at NAVER WEBTOON in Seoul. He has deep on-device ML experience from Samsung Electronics, contributing to NNTrainer and the widely used NNStreamer project to integrate multiple NN backends (including ARMNN) and robust testing flows. Comfortable across the stack, he has built gstreamer-based tensor streaming, Tizen ML APIs, and production services such as a video recommendation server during an internship at LINE. Known for pragmatic engineering, he combines low-level framework integration with deployment-focused testing and automation, making models reliably run on edge devices and production platforms.
code10 years of coding experience
job3 years of employment as a software developer
bookExchange semester, Exchange semester at University of Leeds
bookBachelor's degree, Bachelor's degree at 한양대학교
languagesEnglish, Korean, Japanese
github-logo-circle

Github Skills (8)

neural-network10
tensorflow10
testing9
cprogramming-language9
c-language9
gstreamer8
ai8
tizen6

Programming languages (8)

TypeScriptC#JavaC++ShellCSCSSPython

Github contributions (5)

github-logo-circle
nnstreamer/nnstreamer

Jan 2020 - Jun 2021

:twisted_rightwards_arrows: Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.
Role in this project:
userML Engineer
Contributions:103 reviews, 20 commits, 20 PRs in 1 year 6 months
Contributions summary:Jihoon primarily contributed to improving the NNStreamer project, focusing on enhancements and bug fixes related to neural network frameworks and testing. They made changes to the testing infrastructure to accommodate the disabling of TensorFlow Lite, ensuring tests run correctly. The user also added an NNTrainer enum to the singleshot API, further integrating the project with different NN frameworks. Additionally, they modified code to include support for the ARMNN backend and other NN framework integration improvements.
arrowscaffe2streamtensorflowtizen
zhoonit/powerOverWhelming

May 2017 - Jun 2017

Contributions:41 commits, 4 PRs, 27 pushes in 1 month
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.
Request Free Trial