About Me

Hi, I’m Myeongsoo Kim, an Applied Scientist at AWS AI working on Amazon Q Developer. I’m part of the team developing an AI-powered assistant that helps developers build, debug, and maintain applications. My work focuses on creating intelligent agents that understand code context, generate high-quality code, and assist with complex software engineering tasks using large language models.

I earned my PhD in Computer Science from Georgia Tech, where I worked under the supervision of Prof. Alessandro Orso (now Dean at the University of Georgia’s College of Engineering). My doctoral research focused on software engineering and program analysis. I joined AWS AI in December 2024.

Recent News

• [ICSE 2025 Industry - 🏆 Distinguished Paper Award] “Aster: Natural and Multi-Language Unit Test Generation with LLMs”
  Rangeet Pan, Myeongsoo Kim, Rahul Krishna, Raju Pavuluri, Saurabh Sinha

• [NeurIPS 2025 D&B] “CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance”
  Myeongsoo Kim, Shweta Garg, Baishakhi Ray, Varun Kumar, Anoop Deoras
  [arXiv]

• [FSE 2025] “LlamaRestTest: Effective REST API Testing with Small Language Models”
  Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
  [ACM DL]

• [ICSE 2025 Research] “A Multi-Agent Approach for REST API Testing with Semantic Graphs and LLM-Driven Inputs”
  Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
  [IEEE]

• [ICSE 2025 Demo] “AutoRestTest: A Tool for Automated REST API Testing Using LLMs and MARL”
  Tyler Stennett, Myeongsoo Kim, Saurabh Sinha, Alessandro Orso
  [IEEE]

Research Interests

My research and development work centers on:

• Large Language Models (LLMs) for code generation and understanding
• AI Agents for automated software development
• Software Engineering tools and best practices
• Machine Learning Systems at scale

Publications

You can find my research publications on my Google Scholar profile.

Get in Touch

Feel free to reach out via email or connect with me on LinkedIn and GitHub.