I’m a member of technical staff at OpenAI, where I worked on projects like Jukebox and CLIP. My research interests include large-scale multimodal deep learning and music understanding.
I completed a Ph.D. in Music Technology at New York University, where I focused in music informatics and machine learning, looking for solutions to automatic transcription, source separation, timbre modeling, etc. In the past, I was a software engineer/data scientist at Kakao Corp and NCSOFT Corp developing recommender systems and application servers.
This site serves as a personal portal where you can jump to my Github and LinkedIn pages, browse through blog articles, or check out my bio and CV.