About me

I am an incoming Computer Science Ph.D. student at Texas A&M University, where I am fortunate to be advised by Prof. Kuan-Hao Huang. My research focuses on understanding how large language models represent and process information internally, using those insights to make them fundamentally more reliable, safe, and controllable. My broader research interests span mechanistic interpretability, cross-lingual generalization, and hallucination detection, with the long-term goal of building AI systems that are transparent by design.

Prior to starting my Ph.D., I completed my M.S. at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Hao Peng and Prof. Dilek Hakkani-Tür. My master’s research focused on hallucination detection via hidden-state probing and understanding adversarial jailbreaking dynamics.

Alongside my academic track, I previously worked as a Research Engineer at MathGPT.ai, where I developed education-centric reasoning benchmarks to evaluate how minor linguistic or contextual changes can destabilize model reasoning, and explored how fine-tuning Small Language Models (SLMs) can improve consistency in tutoring applications (paper). Earlier in my research journey, I was a Post-Baccalaureate Research Fellow at RBCDSAI, IIT Madras, working with Prof. Balaraman Ravindran and Dr. Ashish Tendulkar.

When I’m not looking at hidden states or training classifiers, you can find me lifting at the gym or hunting down the best food spots in town.

Let’s Connect! If you are interested in collaborating on mechanistic interpretability, model controllability, or LLM safety, please feel free to reach out via Email or view my CV.