Kyungmin Lee
AI Scientist at LG AI Research
Seoul, South Korea
Summary
🤩
Rockstar🎓
Top SchoolKyungmin Lee is an AI Scientist based in Seoul with eight years of experience focused on efficient large language model inference and deployment. At LG AI Research he has progressed from research intern to AI Scientist working on inference engines such as TensorRT-LLM, FasterTransformer, DeepSpeed and custom tooling like SGLang and MaxText for GPU/TPU acceleration. He combines hands-on systems work in C++/GPU kernels and practical ML integration (Hugging Face, Paxml), bridging research and production-facing inference stacks. Known for squeezing performance out of hardware, he also has roots in computer vision and CPU/GPU parallel system research from his university projects and boostcamp training.
8 years of coding experience
1 year of employment as a software developer
학사, AI융합학부, 학사, AI융합학부 at 숭실대학교
Github Skills (60)
transformers10
pytorch10
benchmark10
language-model10
python10
toolbox10
semantic-segmentation10
openmmlab10
mixture-of-experts10
machine-learning10
inference10
image-segmentation10
data-parallelism10
deepspeed10
deep-learning10
Programming languages (3)
Github contributions (5)
SSU-SSORA/PlatformControlSimulator_Window
Sep 2017 - Nov 2021
Contributions:14 pushes, 2 branches in 4 years 3 months
lkm2835/reinforcement_learning
Mar 2021 - Jan 2022
Contributions:42 pushes, 2 branches in 10 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.