I'm a sophomore at Johns Hopkins University studying Computer Science and Economics. I'm currently researching multi-agent debate systems and collaborative reasoning failure modes at The Normativity Lab, and contributing to the Sorrel open-source framework for multi-agent reinforcement learning at UofT's Social AI Research Group. Interested in AI alignment, normative reasoning, partial observability, and the intersection of technical AI capabilities with policy implications.
What I'm currently doing:
- AI Researcher at JHU Normativity Lab
- External Research Collaborator at Social AI Research Group
- Contributing to Sorrel
- Vice President @ Tech Policy Society at JHU
- Rise Fellow '22 backed by Schmidt Futures and the Rhodes Trust
What I've done in the past:
- Claude Builder @ Anthropic [fall 2025]
- Tech Policy Intern @ AEI [summer 2025]
- Developed an AI Risk Auditor
- Fine-tuned GPT-2 for code explaination
- Intern @ Auctor AI (YC X25)
- Hosted JHU's inaugural AI Policy Hackathon with $25k sponsorship from OpenAI and Microsoft
