Junwon Hwang
AI Scientist at LG AI Research
Yongin-si, South Korea
Summary
👤
Senior🎓
Top SchoolJunwon Hwang is an AI scientist with 10 years of experience applying research-grade machine learning to production systems, currently focusing on LLM optimization, quantization, and inference at LG AI Research. He builds libraries and deployment tooling that bridge cutting-edge model architectures with efficient serving stacks (including TensorRT-LLM and PTQ workflows), and has driven open-source readiness for large models like EXAONE. Previously he shipped trading agents, voice and vision pipelines, and generative-image research at ESTsoft and VoyagerX, giving him a rare blend of applied R&D and product engineering. Based in Yongin-si, South Korea, he pairs deep model-level insight with hands-on MLOps and demo/serving implementations, and has a track record of diagnosing real-world performance bottlenecks beyond algorithmic work.
10 years of coding experience
3 years of employment as a software developer
학사, Computer Software Engineering, 학사, Computer Software Engineering at 성균관대학교
Github Skills (71)
transformers10
python10
deep-learning10
gemma10
cpp10
glm10
multimodal10
llm-inference10
audio10
transformer10
gpt10
nlp10
jax10
data-science10
llama10
Programming languages (10)
Github contributions (5)
nuxlear/source-code-translator
Sep 2022 - Dec 2022
Contributions:20 commits, 18 pushes, 1 branch in 2 months
nuxlear/STROTSS-keras
Aug 2019 - Jan 2020
Keras Implementation of Reproducing "Style Transfer by Relaxed Optimal Transport and Self-Similarity" (CVPR 2019)
Contributions:43 commits, 14 PRs, 54 pushes in 5 months
kerasstyle-transfer
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.