Current Role & Education

I am a Research Engineer II at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), a highly ranked AI university according to CSRankings. I work on interpretability and reasoning in large language models. I earned my M.Sc. in Machine Learning from MBZUAI and my B.Sc. in Computer Science, with a minor in Mathematics, from New York University Abu Dhabi.

Research Interests

My research interests center on interpretability, reasoning, language models, and what I call the physics of intelligence. That is, the search for principles underlying increasingly competent, reliable, and human-aligned intelligent behavior.

Current Research at MINT

I currently work with Dr. Kentaro Inui at the MBZUAI Interpretability Team, also known as MINT, where we study how language and multimodal models represent knowledge, retrieve information, and develop reasoning-like behavior. Motivated by human cognition as a natural reference point for intelligence, I study how mechanistic explanations can help identify the computational structures and representational dynamics that support flexible and reliable reasoning in AI systems.

Research Training & Prior Work

I have been privileged to receive world-class research training from brilliant researchers in AI. I received formative training from Dr. Kun Zhang and Dr. Martin Takáč, and later co-authored RECALL with Dr. Takáč, my first first-author paper as a research engineer at MBZUAI, which appeared in ACL 2025.

I also worked with Dr. Qirong Ho of Petuum on Bayesian optimization for hyperparameter tuning, helping researchers tune AI systems under strict compute and budget constraints. At NYU, I worked with Dr. Farah Shamout at the Clinical Artificial Intelligence Lab on security and interpretability in AI for medical imaging.