[to be placed]
[to be placed]
[to be placed]
I'm Vaishnavi Singh. I study Computing and LawComputing and Law with a double major in Political Science at SMU, in my final year. I work on AI safety and governance.
On the research side: I'm a Georgia Tech AISI Technical FellowGeorgia Tech AISI Technical Fellow, covering RL misspecification, AI control, oversight, and mechanistic interpretability, and alumna of OAISIthe Oxford AI Safety Initiative, where I completed the ARENA curriculum and did ML engineering for AI safety research at ARBOx3 and BASIS Berkeleythe Berkeley AI Safety Student Initiative, where I worked on AI moral status and personhood. That research became a paper accepted to the FAST Workshop at AAAI 2025.
In industry: I'm at ConfideConfide Platform, building an AI governance product covering policy generation, evaluation tooling, and incident reporting, and previously worked in technology risk at KPMGKPMG, in technology risk advisory, reviewing AI systems against the EU AI Act, NIST RMF, and related standards.