I'm a PhD candidate in Computer Science at NYU, where I study how algorithms, data, and institutions create systematic inequalities in who is seen, heard, and valued. My work treats bias in socio-technical systems—social-media platforms, large language models, academic publishing—not as a bug in a single model but as an emergent property of tightly coupled computational and social processes.

My research is organized around three mechanisms: visibility bias (who sees what information), representational bias (how groups are portrayed), and institutional bias (how credit, access, and evaluation are allocated). I study these through an end-to-end approach that moves from measurement—building large-scale datasets and quantifying inequalities—to causation—designing field experiments and algorithmic audits that isolate how platform rules and human decisions jointly produce bias—to mitigation—proposing algorithmic and policy interventions. This work spans two empirical domains: social media and LLMs (auditing recommendation algorithms on YouTube and TikTok, measuring the political behavior of LLMs) and academia and bibliographic systems (uncovering citation manipulation and demonstrating racial and institutional biases in access to scientific knowledge).

My findings have been published in Nature, PNAS Nexus, Scientific Reports, and IEEE, and covered by outlets including Nature, Science, Scientific American, and The Times. I was named to MIT Technology Review's Innovators Under 35 list in 2023. Prior to my PhD, I earned an M.Sc. from the University of Toronto and a B.Sc. from NYU Abu Dhabi.