I’m Seungjae Lim, an M.S. student in the CASYS Lab at KAIST, working at the intersection of research and engineering in machine learning systems. My current focus is on system-level optimization for efficient LLM-based multi-agent serving. I seek opportunities to learn from diverse experiences and continuously evolve in both technical depth and practical impact.
- Korea Advanced Institute of Science and Technology (KAIST), South Korea
- M.S. student, School of Computing
- Research topic : Sustainable Machine Learning System
- Advised by Youngjin Kwon
- Korea Advanced Institute of Science and Technology (KAIST), South Korea
- B.S, School of Computing
- Minor in Electrical Engineering
- Graduated as Top 10 Leadership & Volunteer Honoree
- Chungbuk Science High School, South Korea
- Early Graduation
- CASYS KAIST, South Korea
- ML Systems Research Intern (Jun 2023 – Jun 2024)
- Optimized memory efficiency in speculative-decoding inference serving.
- NAVER CLOVA, South Korea
- ML Engineering Intern (Aug 2022 – Feb 2023)
- Built delivery-time prediction models and an AutoML forecasting pipeline for time-series data.
-
TTServing: Efficiently Serving Large Language Models with Test-time Search for Inference-time Scaling
Sukmin Cho, Seungjae Lim, Sangjin Choi, Hyunsu Ye, Wooseok Gwak, Youngjin Kwon
Under Review -
COSPEC: Efficient LLM Serving with Colocated Speculative Decoding
Sangjin Choi, Hyunjae Lee, Seungjae Lim, Sukmin Cho, Youngjin Kwon
Under Review -
RAG-based Unanswerable Question Detection in Clinical Text-to-SQL
Donghee Han, Seungjae Lim, Mun Yong Yi
CIKM 2025 | The 34th ACM International Conference on Information and Knowledge Management -
Leveraging LLM-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data
Donghee Han*, Seungjae Lim*, Daeyoung Roh, Sangryul Kim, Sehyun Kim, Mun Yong Yi
(*Equal contribution)
COLING 2025 | The 31st International Conference on Computational Linguistics
pdf | abstract
-
Leadership & Volunteer Excellence Award 🥇 | 2025
(KAIST President's Award) Top 10 among all 2024–2025 graduates for exceptional leadership and volunteer work -
Excellence Award (2nd Place) 🥈 | Elice AI Hellothon, 2024
Caregiver cognitive-activity lesson guide creator & elderly interactive AI drawing diary service — SAEM·SAM -
Grand Prize (1st Place) 🥇 | SPARCS Science Hackathon, 2024
(Daejeon Mayor's Award) Web-based XR labs for all types of experiments — ALLeX -
Grand Prize (1st Place) 🥇 | Social Problem-Solving Volunteer Showcase, 2024
(Gyeonggi-do Governor's Award) Generative volunteer reward system — GreenThread -
Gold Prize (1st Place) 🥇 | ICISTS Hackafair, 2024
GenEraser — customizable profanity-filtering B2B service with RAG -
Best Prize (1st Place) 🥇 | Social Problem-Solving Volunteer Idea Hackathon, 2024
Generative volunteer reward system for creating customizable characters — GreenThread -
Best Prize (3rd Place) 🥉 | K-Data Science Hackathon, 2024
Fine-tuned & served distortion-free LLM with RAG on Korean history — K-Hyunmoo GPT -
Top 10 (Finalist) 🏅 | Elice Generative AI Edu Hackathon, 2023
AI Oneul — literacy-promotion app using generative AI with few-shot CoT prompting -
Silver Prize (2nd Place) 🥈 | KAIST-POSTECH-UNIST Data Science Contest, 2023
ECMiner Award — Business-owner prediction & pop-up / survey ad planning with Hana 1Q usage data -
Best Prize (1st Place) 🥇 | Social Problem-Solving Volunteer Idea Hackathon, 2023
Real-estate listing & brokerage recommendation app for single female-headed households — Homey -
Grand Prize (1st Place) 🥇 | Korean Donation for Education Idea Contest, 2023
(Minister of Science and ICT Award) Dynamic coding-based fairy-tale platform for English education
| Event | Period | Experience |
|---|---|---|
| CASYS KAIST | 2021.06 ~ 2021.08 | Research Student in ML Security |
| OSLab KAIST | 2021.09 ~ 2021.12 | Research Student in OS |
| MLML KAIST | 2022.06 ~ 2022.08 | Research Student in AutoML |
| Mad Camp | 2021.12 ~ 2022.01 | Developer |
| NAEK YEHS | 2023.01 ~ | Member |