Summary
Seunggeun Chi is an Applied Scientist at Amazon Music with a Ph.D. in Artificial Intelligence from Purdue and eight years of experience translating advanced computer vision and multi-modal modeling research into product-grade systems. His work spans Gaussian splatting, human-object interaction, and pose estimation, and he now applies those spatial and visual modeling techniques to audio and music using multi-modal foundation models and LLMs. He has built diffusion-based solutions for fusing heterogeneous sensor streams (IMU, head trajectory, video) during a Meta research internship and developed generative models for future human action affordances at Honda Research. Based in San Francisco, he combines rigorous academic training with field-tested leadership from his time as a squad leader in the Korean Army, where he managed logistics and operations in austere conditions. This blend of hands-on systems experience, deep research expertise, and operational discipline informs his work on intelligent music experiences and multimodal understanding.
8 years of coding experience
1 year of employment as a software developer
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Seoul National University
Doctor of Philosophy - PhD Artificial Intelligence, Doctor of Philosophy - PhD Artificial Intelligence at Purdue University
English, Korean