I'm an applied researcher interested in bridging the socio-technical gap in AI systems

I am passionate about developing tools and methodologies that connect the technical aspects of AI systems with their societal implications. My work focuses on robust evaluation methodologies, responsible deployment strategies, and governance mechanisms that ensure oversight of AI technologies.

Currently, I am an Applied Research Scientist at Alinia AI where I research and build tools for responsible AI deployments, AI evaluations, and safeguards. I am also a Working Group Chair at the EvalEval Coalition, where I co-lead research to further robust AI evaluations.

Previously, I researched context-specific LLM development to address misalignment in AI system deployments at the MIT CSAIL Algorithmic Alignment Group (under the guidance of Dylan Hadfield-Menell), chaired the MIT AI Ethics & Policy Group, interned with Waymo on improving Pre-Release Evaluations of the Waymo Driver, led the publication of Volume V of the MIT Science Policy Review as CEO, and was awarded a Research Fellowship at NYU Abu Dhabi to investigate the societal impacts of recommender systems.