AWS Agentic AI
AgentCore Evaluation
Core contributor to AgentCore Evaluation; co-led first-party evaluation model training and evaluation for agent evaluation.
About
I am an Applied Scientist II at AWS Agentic AI, where I work on AgentCore Evaluation and Strands Agents. I received my Ph.D. in Computer Science and Engineering from POSTECH, advised by Prof. Suha Kwak. During my Ph.D., I collaborated with Ivan Laptev. I also interned under and closely worked with Douglas Gray at Amazon.
At AWS, I contribute to agent evaluation systems for production agentic AI, including AgentCore Evaluation and Multimodal Evaluators. Previously at Amazon Core Search, I contributed to Amazon Lens Live through multimodal retrieval, result verification, and MLLM-based re-ranking. During my internship, I developed GENIUS, a generative retrieval framework for universal multimodal search.
My research focuses on reliable agentic AI systems, agent evaluation, agentic retrieval, multimodal retrieval, MLLM-based retrieval and ranking, long-horizon LLM agents, agent memory and context management, and representation learning. I am also interested in VLA robot learning, reinforcement learning, PPO, and GRPO.
Products
Amazon Core Search
Amazon Lens Live
Contributed to multimodal retrieval, result verification, and MLLM-based re-ranking for real-time visual shopping search.
Experience
-
Applied Scientist II — Agentic AIAmazon Web Services · Bedrock AgentCore & Strands Agents
- Core contributor for Multimodal Evaluators in Strands Evals and AgentCore Evaluation.
- Co-led first-party evaluation model training and evaluation for agent evaluation.
-
Applied Scientist II — Core SearchAmazon.com · Visual Search (Amazon Lens Live)- Contributed to multimodal retrieval, verification, and MLLM-based re-ranking for Amazon Lens Live.
-
Applied Scientist Intern — Core SearchAmazon.com · Manager: Douglas Gray
- Worked with Douglas Gray to develop GENIUS, a generative retrieval framework for universal multimodal search; published at CVPR 2025.
Publications
International Conference
-
-
-
-
FREST: Improving Robustness of Semantic Segmentation via Source-free Domain Adaptation with Feature RestorationECCV 2024 -
PromptStyler: Prompt-driven Style Generation for Source-free Domain GeneralizationICCV 2023 -
HIER: Metric Learning Beyond Class Labels via Hierarchical RegularizationCVPR 2023Qualcomm Fellowship Finalist -
-
-
-
Embedding Transfer with Label Relaxation for Improved Metric LearningCVPR 2021BK21 / IPIU Best Paper -
-
Deep Metric Learning Beyond Binary SupervisionCVPR 2019Oral · 5.58% · 140+ citations
Preprint
Technical Blog
Education
-
Ph.D., Computer Science and EngineeringPohang University of Science and Technology (POSTECH)- Advised by Prof. Suha Kwak.
- Dissertation: Towards Retrieval at Scale via Compact Embeddings and Generative Modeling.
- Graduated with the highest distinction across the CSE, GSAI, EE, and CITE departments (press).
-
B.S., Undergraduate StudiesDaegu Gyeongbuk Institute of Science and Technology (DGIST)
Honors & Awards
- Graduated with the highest distinction across the CSE, GSAI, EE, and CITE departments (2025) · press
- Qualcomm Innovation Fellowship Korea (2024) · Winner — Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
- Google PhD Fellowship Program (2023)
- BK21 Best Paper Award (2023) · Winner — Self-Taught Metric Learning without Labels
- BK21 Best Paper Award (2023) · Winner — Combating Label Distribution Shift for Active Domain Adaptation
- Qualcomm Innovation Fellowship Korea (2022) · Winner — Self-Taught Metric Learning without Labels
- Qualcomm Innovation Fellowship Korea (2022) · Winner — Combating Label Distribution Shift for Active Domain Adaptation
- BK21 Best Paper Award (2022) · Winner — Embedding Transfer with Label Relaxation for Improved Metric Learning
- IPIU Best Paper Award (2022) · Gold Prize — Offline Active Domain Adaptation
- ICT Paper Contest (2021) · 2nd Place — Deep Metric Learning Beyond Binary Supervision
- SKT AI Fellowship (2021)
- POSTECHIAN Fellowship (2021)
- IPIU Best Paper Award (2021) · Grand Prize — Embedding Transfer with Label Relaxation for Improved Metric Learning
- Naver Ph.D. Fellowship (2020)
- Qualcomm Innovation Fellowship Korea (2020) · Winner — Deep Metric Learning Beyond Binary Supervision
Professional Service
- Conference ReviewerCVPR, ICCV, ECCV, ICLR, ICML, NeurIPS, AAAI, ACCV
- Journal ReviewerIEEE TPAMI, IJCV
Patents
- Rehabilitation program creation method for muscle treatment and providing apparatusKR101648638B1, Republic of Korea