Summary
Younghan Park is an undergraduate researcher and software engineer specializing in multimodal deep learning with a focus on vision-language and speech-language unification. Currently an exchange researcher at UT Austin, he has built large-scale datasets and benchmarks for podcast highlight detection and conversational text-to-speech evaluation. His industry experience includes voice-tech research at NAVER Cloud and VLM-based anti-cheat work for PUBG at KRAFTON, demonstrating an ability to move research into product contexts. As a co-founder of an assistive-technology startup, he holds a patent for an oral-cavity input device, highlighting a practical, user-centered inventiveness beyond academia. A former KATUSA military sergeant, he brings discipline and cross-cultural communication skills to collaborative research teams. Based in Austin with roots in Seoul, he combines eight years of practical engineering experience with a strong research portfolio in multimodal AI.
7 years of coding experience
5 years of employment as a software developer
Exchange Student Computer Science, Exchange Student Computer Science at The University of Texas at Austin
Bachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at Yonsei University
Korean, English