Dongjae Lee

Formal Methods × Agentic AI for Reliable Programming Systems

Welcome.

I am Dongjae Lee, a Ph.D. student in the School of Computing at KAIST and a member of Prosys Lab, advised by Kihong Heo.

Portrait of Dongjae Lee

Research Interest

  1. Verified AI programming

    AI agents that produce not only implementations but proofs of their correctness, by pairing AI programming with formal verification.

  2. Specification languages for verified AI programming

    Writing specifications is the bottleneck in verified AI programming. I design specification languages that stay precise and easy to read.

  3. Neuro-symbolic agent safeguards

    Verifying the safety of an AI agent's actions with formal techniques, and building guardrails on top of those verifications.

Publications

Education

  • Ph.D.

    School of Computing, KAIST — 2026–Present

  • M.S.

    School of Computing, KAIST — 2024–2026

  • B.S.

    School of Computing, KAIST — 2020–2024

Honors

  • 2026

    Master's Thesis Excellence Award

  • 2025

    Winner — AI Champion Competition

    Outstanding Teaching Assistant — CS424 Program Reasoning

  • 2024

    B.S. Summa Cum Laude — GPA 4.03/4.3

    Finalist — Global AI Idea Lab Contest, CODEGATE

  • 2022

    National Excellence Scholarship — 2022–2023

  • 2021

    Dean's List — Fall 2021

  • 2020

    Dean's List — Spring 2020