I was born and raised in South Korea and moved to the U.S. in my junior year of high school as a foreign exchange student in 2013. I studied mathematics and computer science during my undergraduate years and have 4.5 years of experience as a software developer and data engineer at both startups and large companies. I’m currently pursuing a Master’s degree at Cornell Tech, where I enjoy learning new technologies and applying them to real-world products.

I am interested in machine learning, generative AI, and vertical AI applications in real business domains.

I’m building an ML pipeline to improve breast cancer classification using data augmentation (torchvision) and generative AI (VAE, Stable Diffusion, ControlNet). I fine-tuned Stable Diffusion v1.5 with Low-Rank Adaptation (LoRA) which led to an 11.04% increase in classification accuracy, improving performance from 71.63% to 82.67%. I fine-tuned the ControlNet model with tumor mask images as control signals alongside text prompts which led to an 11.32% performance boost in classification accuracy.