Background
I started at Anthropic as a Fellow in the Anthropic Fellows Program, then joined the alignment org. Before that, I was at AWS Agentic AI, where I worked on an AI safety guardrail, Automated Reasoning checks (ARc).
I completed my PhD at Carnegie Mellon University’s security lab, CyLab, where I was advised by Limin Jia. My PhD research was focused on practical analysis of security properties for software systems through program analysis and type system design.
As an undergraduate, I was a researcher at the UVa Security Research Group under the guidance of Professor David Evans, and worked on the Obliv-C project.
Internships
- AWS Automated Reasoning Group, 2022
- Facebook Research, 2021 and 2019
- Center for Open Science, 2016
- NASA Goddard Space Flight Center, 2016
Service
Program committee member:
- ACM Conference on Computer and Communications Security (CCS): 2026, 2025
- International Symposium on Formal Methods (FM): 2026
- The Web Conference (TheWebConf): 2026
- Workshop on Measurements, Attacks, and Defenses for the Web (MADWeb): 2025
Artifact evaluation program committee member:
- Privacy Enhancing Technologies Symposium (PETS): 2025, 2024, 2023 (Distinguished Artifact Reviewer, 2025)
- ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA): 2024
- European Symposium on Programming (ESOP): 2022
External reviewer: PETS ‘23, NDSS ‘23, NDSS ‘22, S&P ‘22, NDSS ‘21.