Summary
Yoonho Shin is an AI engineer based in Seoul with eight years of hands-on experience building vision AI systems and a decade-long focus on visual intelligence and vision-language models (VLM). At LG Uplus he designs and ships agentic VLM solutions, sports highlights and talking-face generation pipelines, and commercial image/video generation for marketing, alongside earlier AI CCTV work. His PhD research at LG Graduate School of AI centers on VLM-based video recognition, bridging academic rigor with product-focused engineering. Yoonho combines signal processing foundations from Korea University with practical production expertise, enabling end-to-end deployments of video and generative models. He is comfortable moving between research prototyping and scalable systems engineering, often tackling multimodal fusion and real-time inference challenges. Colleagues note his ability to turn advanced VLM research into tangible media and surveillance applications for enterprise use.
7 years of coding experience
Master of Engineering - MEng Multimedia and Signal processing, Master of Engineering - MEng Multimedia and Signal processing at Korea University
Doctor of Philosophy AI, Doctor of Philosophy AI at LG Graduate School of AI