Minjae Leemjbooo@kaist.ac.kr |
|
About
I am an AI Algorithm Researcher at FuriosaAI, where I focus on efficient language model inference and test-time scaling. My general research interest is developing active agents for medical decision-making that learn generalizable knowledge from heterogeneous healthcare data and adapt to local contexts through inference. My work spans:
- Inference in Language Models: Efficient and agentic inference for scalable language models, with a focus on speculative decoding, test-time compute scaling, and reasoning.
- Healthcare Machine Learning: Automated clinical decision-making using electronic health records (EHRs), including representation learning, encoding, synthesis, and privacy-preserving data sharing.
I received my M.S. from the Kim Jaechul Graduate School of AI (GSAI) at KAIST, advised by Edward Choi, where I wrote my thesis on Exploring Optimal Encoders for Electronic Health Records. I completed my B.S. in Industrial & Systems Engineering at KAIST with Summa Cum Laude honors (ranked 1st in department; GPA 4.0/4.3).
Publications
Experience
|
AI Algorithm Researcher FuriosaAI, Seoul, South Korea Research on efficient LLM inference and test-time scaling; research partnerships and academic collaborations with Berkeley AI Research (BAIR) and UW–Madison
|
Mar. 2023 – Present |
|
Post-M.S. Research Assistant KAIST, Seongnam, South Korea EHR synthesis and transfer learning with clinical collaborators, contributing to a multicenter study
|
Jul. 2023 – Jul. 2024 |
|
Research Intern NAVER CLOVA, Seongnam, South Korea Model quantization and compression techniques for efficient AI inference
|
Dec. 2021 – Feb. 2022 |
Education
|
M.S. in AI Kim Jaechul Graduate School of AI (GSAI), KAIST, Seongnam, Korea Advisor: Edward Choi | Thesis: Exploring Optimal Encoders for Electronic Health Records |
Mar. 2023 |
|
B.S. in Industrial & Systems Engineering; Minor in Economics KAIST, Daejeon, Korea Summa Cum Laude (ranked 1st in department; GPA 4.0/4.3) |
Feb. 2021 |
|
Exchange Program in Informatics (Informatik) Technische Universität Berlin (TUB), Berlin, Germany Mirae Asset Outbound Exchange Student Scholarship |
Apr. – Jul. 2017 |
Invited Talks & Teaching
|
Optimizing AI Efficiency from Silicon to Model MODULABS, 100+ attendees Invited talk on the growing importance of inference over training in the LLM era and FuriosaAI's full-stack approach to efficient inference
|
2026 |
|
Language Models in Clinical ML: My Journey with Two Questions Center for Advanced Medical Computing and Analysis (CAMCA), Harvard Medical School / MGH Research talk on scalable, unified text-based approaches for EHRs and cost-efficient inference for language models
|
2025 |
|
How Will DeepSeek-R1 Impact Education's Future? College of Education, Chungnam National University Invited talk on LLM fundamentals, DeepSeek-R1, and educational impacts; 30+ educational staff and students
|
2025 |
|
Summer Session for Medical AI (CNN for Chest X-ray classification) Korean Society of Artificial Intelligence in Medicine (KoSAIM), 100+ medical staff and students Introductory course on CNN theory and practice for chest X-ray classification
|
Summer 2023 |
|
AI Short Course Program (Diffusion models) Korean Artificial Intelligence Association (KAIA), 100+ attendees Introductory course on diffusion model theory and practice
|
Spring 2023 |
|
Machine Learning for Healthcare (AI612) – Teaching Assistant KAIST Graduate Course, 200+ students (Instructor: Edward Choi) |
Spring 2022 |
|
Programming for AI (AI504) – Teaching Assistant KAIST Graduate Course, 200+ students (Instructor: Edward Choi) 🏆 Best Lecture Award (Fall 2021) |
Fall 2021, Fall 2022 |
Academic & Leadership Initiatives
|
Lab Synchronization Seminar GSAI KAIST Launched a seminar series for sharing and discussing ongoing research topics
|
Sep. 2022 – Mar. 2023 |
|
Lab Tech-talk for Diffusion Models GSAI KAIST Led technical seminar sessions on diffusion models, including Improved DDPM, classifier-free guidance, and structured discrete-state diffusion models
|
Mar. 2022 – Mar. 2023 |
|
Head of the Bureau of Social Participation KAIST Undergraduate Student Council Directed projects to support labor rights, learning rights, and privacy for campus members
|
Sep. 2017 – Dec. 2018 |
Awards & Honors
| Summa Cum Laude (ranked 1st in department; GPA 4.0/4.3), KAIST | 2021 |
| National Science and Technology Scholarship, Ministry of Science, Korea | 2021 – 2022 |
| Outbound Exchange Student Scholarship, Mirae Asset | 2017 |
| Dean's List (Departmental Academic Excellence Scholarship, 2nd place), ISE, KAIST | 2016 |
| National Science and Technology Scholarship (merit-based), Ministry of Science, Korea | 2015 – 2016 |
| National Science and Technology Scholarship, Ministry of Science, Korea | 2013 – 2016 |
Academic Services
| Reviewer – International Conference on Machine Learning (ICML) | 2026 |
| Reviewer – Machine Learning for Health Symposium (ML4H) | 2023 – 2025 |
| Reviewer – Machine Learning for Healthcare (MLHC) | 2025 – 2026 |