Jihwan Eom
Technical Lead at Kakao Corp
Seoul, South Korea
Summary
🤩
Rockstar🎓
Top SchoolJihwan Eom is a technical lead and AI researcher based in Seoul with five years of hands-on experience building label-efficient computer vision and multimodal systems. He has driven production ML features across messaging and healthcare—shipping on-device multilingual vector search and real-time image captioning at LINE Plus, and pioneering radiology image-to-text models and in-domain weight initialization at KakaoBrain. Currently leading long-context and video understanding efforts and contributing to multimodal LLM hybrid reasoning at Kakao, he blends research depth in semi/self-supervised learning, domain adaptation, and test-time adaptation with product-focused engineering. Collected experience at Intel and academic projects shows a pattern of turning noisy, imbalanced real-world data into robust models, and an appetite for tackling problems beyond conventional CV boundaries.
5 years of coding experience
5 years of employment as a software developer
B.S., Computer Science, B.S., Computer Science at Yonsei University
Stackoverflow
11reputation
34reached
0answers
1question
Github Skills (117)
benchmark10
mmsegmentation10
anomaly-detection10
toolbox10
mscoco10
datasets10
semi-supervised-learning10
deep-learning10
coco10
automl10
quantization10
optimization10
imagenet10
openmmlab10
video-understanding10
Programming languages (3)
Github contributions (5)
JihwanEom/datumaro
Apr 2023 - Jun 2023
Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.
Contributions:2 PRs, 62 pushes, 7 branches in 1 month
JihwanEom/JihwanEom.github.io
Dec 2020 - Apr 2022
Contributions:17 pushes, 2 branches, 1 comment in 1 year 4 months
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.