Experience

Industry and research experience, education, awards, and technical skills.

Korea University mark

Senior Researcher - Human-Inspired AI Research, Korea University

Aug 2024 - Present | Seoul, Republic of Korea

  • Context: Promoted from Researcher in recognition of founding and leading KUDoc, as HIAI expanded into an institute with broader scope across multimodal document AI, RAG, and applied AI systems.
  • Contribution: Set the research direction for structure-aware chunking, LVLM parsing, evidence assembly, and production-oriented QA pipelines; drive external collaborations with Samsung F&M, Hyundai Mobis, and KIGAM.
  • Impact: First-author acceptances at ACL 2026, CVPR 2026, and EMNLP 2025; reduced manual search by ~40% and improved hybrid QA reliability by ~10% across 4 production pilots, supporting 3 technology transfers.

Additional model development: Mi:deum K 1.0, KULLM, Ko-Gemma, and the National Representative K-AI Research Team across academic, industrial, and consortium settings.

Related: HiKEY · M3DocDep · MultiDocFusion · Synerpeace

Korea University mark

Founder & Lead - KUDoc, Korea University Document AI Research Group

Mar 2024 - Present | Seoul, Republic of Korea

  • Problem: Document AI research needed coordinated group-level capacity that no individual researcher could sustain across parsing, retrieval, RAG, and industrial deployment.
  • Contribution: Founded KUDoc and shaped its research agenda across document understanding, multimodal RAG, evaluation, and applied AI; built collaborative programs with Konkuk, Soongsil, and partner labs; lead and advise members from problem formulation through publication and transfer.
  • Impact: KUDoc has produced 13 publications and 13 manuscripts currently under review at top-tier venues (including 4 first-author papers at ACL, CVPR, and EMNLP), 5 patents, 4 major industry–academia projects with 3 technology transfers, and 7 awards.

Related: KUDoc site · DocGraph Copilot · Synapse

Korea University mark

Researcher - Human-Inspired AI Research, Korea University

Jun 2023 - Aug 2024 | Seoul, Republic of Korea

  • Problem: Industrial partners needed reliable multimodal document understanding and hybrid QA pipelines that could handle noisy, heterogeneous long-context inputs.
  • Contribution: Developed ML & NLP systems at HIAI — including structure-aware chunking prototypes, hybrid table–text readers, and domain-specific RAG frameworks for power-plant and industrial settings.
  • Impact: Delivered the EMNLP 2024 Industry paper (co-first author) and an Applied AI Journal study on hybrid table–text QA; laid the technical foundation that led to KUDoc and the subsequent Senior Researcher promotion.

Related: StyleDFS · Hybrid Reader over Tables and Text

Pusan National University mark

Researcher (M.S.) - AI Lab, Pusan National University

Sep 2020 - Feb 2023 | Busan, Republic of Korea

  • Problem: Korean NLP lacked robust systems for recovering explicit linguistic and tabular structure from real-world text and semi-structured data.
  • Contribution: Led neural-symbolic Korean dependency parser and table QA system development within national AI projects.
  • Impact: Achieved state-of-the-art results on Korean parsing and table QA benchmarks; received an Outstanding Paper Award.

Related: Neural Symbolic Models · Hybrid Reader over Tables and Text · Exobrain WiseQA

Pusan National University mark

Researcher - SW Education Center, Pusan National University

Mar 2020 - Aug 2020 | Busan, Republic of Korea

  • Problem: Programming courses needed scalable automated assessment and personalized feedback for students.
  • Contribution: Built a Django-based online judge with auto-grading and recommendation features end-to-end.
  • Impact: Deployed the platform for university programming courses, enabling automated evaluation at scale.

Related: AI-Based Online Judge Program

Education

Pusan National University mark

M.S. in Artificial Intelligence - Pusan National University

Mar 2021 - Feb 2023

  • Advisor: Prof. Hyuk-Chul Kwon — one of Korea's first AI Ph.D.s and an authority on parsing.
  • Thesis: Structure-aware parsing for Korean NLP and question answering, integrating morphological, syntactic, and semi-structured representations for robust downstream reasoning.
  • Contributed to national AI projects (Exobrain WiseQA, KT TTS) and filed patents on hybrid neural-symbolic NLP and adaptive learning systems.
Pusan National University mark

B.S. in Computer Science and Engineering - Pusan National University

Mar 2016 - Feb 2021

  • Advisor: Prof. Jeongu Kim (Mar 2018 – Jun 2020).
  • Undergraduate research in Prof. Hyuk-Chul Kwon's AI Research Lab (Jul 2020 – Feb 2021): contributed to C++-based knowledge graph projects (Korean grammar correction, Korean TTS) and studied transformer-based language models (BERT, RoBERTa, ELECTRA) for Korean NLP.
  • Core coursework in software engineering, algorithms, and data analysis; participated in industry projects and hackathons.

Awards

Deputy Prime Minister and Minister of Education Award NRF · 2024
Outstanding Paper Presentation Award KIISE · 2023
Grand Prize, LLM MVP Competition Samsung F&M · 2023
Excellence Award, KU-Grant Technology Track Korea University · 2023
Outstanding Paper Presentation Award KSC · 2022
Excellence Award, Graduate School of AI PNU · 2022
Milestone Scholarship (Grade A) PNU · 2020

Skills

Modeling

LLM/LVLM fine-tuning Hierarchical retrieval Knowledge graphs Hybrid neural-symbolic reasoning Rule-based evidence filtering

Document AI

Multimodal parsing Hierarchical chunking Layout-aware processing Table/document QA

Programming

Python SQL C/C++ Java

ML & LLM Frameworks

PyTorch HuggingFace Transformers PEFT/LoRA Accelerate OpenAI API Anthropic API

Retrieval, RAG & Evaluation

FAISS Elasticsearch Pinecone LangChain LlamaIndex lm-eval-harness

Document Processing

PyMuPDF pdfplumber Tesseract PaddleOCR LayoutLMv3 Donut

Languages

Korean (native) English (professional working proficiency)

Teaching and Mentoring

Korea University mark

Research Mentor - KUDoc, Korea University

2024 - Present | Seoul, Republic of Korea

  • Mentor 3 M.S. students and 2 Ph.D. students on document AI, multimodal RAG, and structured evidence reasoning.
  • Co-authored 13 publications and 13 manuscripts currently under review at top-tier venues with mentees.
Pusan National University mark

Teaching Assistant & Research Mentor - Pusan National University

2019 - 2022 | Busan, Republic of Korea

  • PNU Software Hackathon (2021): As TA for Prof. Hyuk-Chul Kwon's Software Design course, mentored 100+ students across 30+ projects; seven student teams won awards including the Grand Prize.
  • Capstone research mentoring (2021–2022): Mentored undergraduate capstone teams on Korean dependency parsing and Table QA; one team achieved SOTA on the KLUE-DP benchmark.
  • Course teaching assistant: Software Design (Android, Java) and Web Application Programming under Prof. Hyuk-Chul Kwon; Programming Principles (C) under Prof. Eunmi Jeong.