Summary
Sehun Heo is an AI Modeling Engineer based in Seoul with 10 years of experience specializing in NLP, model fine-tuning, and production serving of open-source large language models. At Hanwha Life AI LAB he leads R&D on LLMs and AI agents, fine-tuning Llama3 and Qwen families for complex document QA and function calling, and deploying models with vLLM and SGLang. Previously he led machine learning efforts at Lomin, building multimodal document-understanding systems that fuse OCR, image, text, and layout signals. Comfortable with Python and PyTorch, he combines research rigor with practical engineering to move models from prototype to production. He brings a background in academic research and an international capstone experience from Purdue, reflecting a blend of collaboration, applied research, and system-level deployment.
9 years of coding experience
1 year of employment as a software developer
학사, Computer Engineering, 학사, Computer Engineering at 충남대학교