About

I am an Applied Scientist at Amazon AWS AI, where I work on building agentic chat assistant with tool calling capabilities. My research focuses on tool attribution and long context management of the chat assitant.

I earned my Ph.D. in Computer Science from University of Maryland, College Park, where I was a member of CLIP lab and was advised by Prof. Rachel Rudinger. During my doctoral studies, my research focussed on long context understanding, preference-aligned text generation using RL rewards, and reasoning with a focus on evaluating LLMs for various capabilities by designing novel tasks, identifying social biases, and attributing the generated text for building trustworthy, and verifiable AI systems.

Previously, I was a researcher at Adobe Research (India) and I am fortunate to have been able to continue my collaboration with them on long document understanding and answer attribution during my Ph.D. I completed my undergraduate studies at IIT Guwahati. During my Ph.D., I was a Research Intern at Meta FAIR under the supervision of Maha Elbayad on analyzing text representations for large language modeling.

Link to Resume