About Me

Hi! I’m Wooil, a first-year MS student in Electrical and Computer Engineering at the University of California - San Diego.

Before returning to academia, I worked as a Machine Learning Research Engineer at LG Electronics. Over three years, I designed end-to-end training and inference pipelines for edge-deployed speech models, achieving a 98% recognition rate on flagship appliances while optimizing for strict hardware constraints. My technical expertise includes a wide range of skills from Python-C feature extraction APIs to modern deep learning architectures in pytorch.

Currently, I am expanding my focus to generative AI, building Claude-based agentic systems with vector databases and exploring novel latent space reasoning architectures for LLMs. Specifically, I am currently investigating variable-length latent space reasoning by extending the “Coconut” architecture to enable dynamic test-time compute allocation.

I am actively seeking a 2026 summer internship in AI/ML. Feel free to connect with me at [email protected]!