Taewan Kwon Email & Phone Number

I am currently working at Liner, focusing on the development of advanced techniques in RAG(retrieval-augmented generation), summarization using LLM.I have experience in developing the LLM-RAG engine for AI chatbot services in OKESTRO. I graduated from Korea University, Department of Electrical Engineering.I am independently writing a research paper on summarization. Also, I am posting insightBriefs, a newsletter with "un-brief" insights into the latest research papers 🗞️🗞️🗞️. 🚀 Work Experience• Working on methodology to build a benchmark dataset to evaluate the LLM-RAG performance• Worked on generative AI chatbot for cloud computing at OKESTRO• Worked on highlighting features for a marketing analytics service at OKESTRO💡 Key Highlights• Experience in the development of product-level LLM-RAG-based chatbot• Developed an LLM-RAG system answering from 150,000+ documents in the cloud computing domain• Created a RAG evaluation dataset with annotations for multi-chunk retrieval, multi-document retrieval, and human-level specific answer• Strong understanding of extractive summarization and currently writing a paper on extractive summarization• Developed TensorBricks, a PyTorch-based framework for high-level development of image models, as a personal projectFeel free to send me a message or reach out for a coffee chat :) ☕️

• 

  Korea University / 고려대학교

  Electrical Engineering