Vachagan Melikian

/vɑt͡ʃʰɑˈɡɑn mɛliˈkjɑn/

I recently graduated from Rutgers University, where I studied Computer Science, Cognitive Science, Linguistics, and Philosophy. I care about technical AI safety and governance.

I founded RAISE, the Rutgers AI Safety Exchange, a student organization building career pathways into AI safety. This summer, I’m joining the Oxford AI Safety Initiative (OAISI) for ARBOx, its alignment research bootcamp.

I’ve interned as a software engineer at Twitch, working on the Twitch app for Android, and at Fidelity Investments on the Fidelity Health app for iOS.

As a fellow at the Rutgers Center for Cognitive Science, I researched the syntax–semantics interface, working with Shannon Bryant and Kristen Syrett. Earlier, at the SHIRE Lab, I developed computational approaches to identifying intersectional biases in large language models.