
Large Language Models (LLMs)
The Project aims to identify pitfalls in LLM evaluation, focusing on LLM alignment with human values
PhD in Computer ScienceNorth Carolina State University
I am an AI Researcher passionate about advancing the capabilities of Generative AI and Large Language Models (LLMs) to solve real-world problems. I specialize in transer learning, model customization and evaluation, and multi-agent social simulations. My current research focuses on three key areas: Model Interpretability, aimed at developing interpretable vector subspaces for text representations; Multi-Agent Social Simulations, aimed at building agentic evaluation testbeds for LLMs to study information diffusion in social networks; and Detecting Value Misalignment in Software Artifacts, aimed at early identification of value misalignment within the software lifecycle by analyzing code-related discussions between developers using LLMs.
I completed my Ph.D in 2025 from the Computer Science department at the NC State University. My academic advisor was Distinguished Professor Munindar P. Singh. My dissertation combines language models and multiagent social simulations to analyze online news discourse and its influence on social media users. Before beginning my Ph.D., I completed my Master’s thesis under the advisement of Dr. Collin F. Lynch .
At NC State University, I have been an active member of the AI in Society group, and helped organize and host several of its early seminars. I have contributed to the development of teaching materials for graduate-level courses, including Natural Language Processing (CSC 791) and Social Computing and Decentralized AI (CSC 555). I served as Head of Events (2022) and later as President (2023) of the Indian Graduate Student Association (IGSA) – Maitri, leading initiatives to support and connect the international student community at NC State. My contributions have been honored by NC State University with awards such as Outstanding Student Leader (2023) and Outstanding Teaching Assistant (2021) .
My industry experience includes two years as a Member of the Technical Staff at Oracle, working on public cloud software deployment infrastructure, and shorter stints as a Machine Learning Engineer Intern for companies including Lenovo, Seagate, and Coupang. I served as a Research Fellow at the Laboratory of Analytic Science for SCADS (Summer Conference on Applied Data Science) 2024. I have been working at LexisNexis as a Data Scientist since April, 2025.
The Project aims to identify pitfalls in LLM evaluation, focusing on LLM alignment with human values
The Project aims to evaluate political correctness in LLMs using a multiagent social simulation for evaluation
The project aims to produce computational models to differentiate war and peace journalism. We apply contrastive learning using Siamese network training on LLMs
The Project aims to understand the influence of news via social media through emotion and moral analysis
I was born and grew up in Varanasi, India. I lived in Bangalore, India for six years before moving to the US. Post work, you can find me working out at the gym, jamming music with friends (I am a flutist), listening to a podcast, or reading a book. I love hiking and being amidst nature. My latest expedition is to hike in all US National Parks (I have covered 12 so far)
Here's my resume.