My research encompass training, alignment, and benchmarking of language models. With the growing integration of AI into our daily lives, I am passionate about developing safe and robust AI systems.
I am currently part of the research group at ServiceNow where my work focuses on enhancing LLMs in post-training phase through data curation, alignment, tool-augmented reasoning, and benchmarking.
Prior to that, I was an AI Resident
at Facebook AI Research, where I worked with Marcus Rohrbach
on developing models with Multimodal understanding of vision and language content.
During my Masters, I worked on evaluating the robustness and generalization of language models as part of my thesis at IIIT Hyderabad.
More details are available in my cover letter.