Work
Research and professional experience.
Industry
AI Governance Intern
Confide Platform
2024 – Present
Working on AI governance tooling for policy generation, evaluation, and incident reporting.
Research
AI Safety Fellowship
BASIS — Berkeley AI Safety Initiative
2025
Research on AI moral status and personhood. Paper accepted to the FAST Workshop at AAAI 2026.
Research
ML Engineering Research Participant, ARBOx3
Oxford AI Safety Initiative (OAISI)
2026
Completed the ARENA curriculum and contributed ML engineering to AI safety research at ARBOx3.
Publications
From Object to Other: A Practical Theory of AI Moral Status in Re-evaluating AI Safety Methods
Presented at the Foundations of Agentic Systems Theory (FAST) Workshop, AAAI 2026, January 27, 2026
View PDF