I’m a PhD student in Artificial Intelligence (Intelligent Systems) at the University of Pittsburgh’s School of Computing and Information, advised by Prof. Zheyuan Ryan Shi.
I study natural language processing, multilingual evaluation, and reliable LLM agents for healthcare. My work asks how language and phrasing affect model decisions, and how to make those decisions more reliable.
At the University of Pennsylvania, I studied transformer interpretability with Prof. Li Shen. I was also a Data Science for Social Good Fellow at UW Seattle.
My education also spans the liberal arts through the Young India Fellowship at Ashoka University. Before graduate school, I worked on science and technology policy at NITI Aayog, the Government of India’s apex policy think tank.
University of Pittsburgh2025–present
PhD in Intelligent Systems · School of Computing and Information
University of Pennsylvania2023–2025
M.S.E. in Scientific Computing · Focus in artificial intelligence
Ashoka University2019–2020
Young India Fellowship · Postgraduate Liberal Studies
Manurag Khullar, Utkarsh Desai, Poorva Malviya, Aman Dalmia, and Zheyuan Ryan Shi. “Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real-World Setting.” In: Proceedings of EMNLP 2026: Industry Track. To appear. 2025 Amazon Research Award Covered in The Hindu BusinessLine
This work led to a 2025 Amazon Research Award supporting continued research (PI: Ryan Shi).
Manurag Khullar, Tanmay Shetty, and Zheyuan Ryan Shi. “Characterizing Paraphrase Inconsistency through Representational Geometry in LLM-Based Clinical Triage.” 2026. Under review.
Teaching Assistant, Applied Machine Learning, Penn (Spring 2025).
Reviewer: AAAI 2026, WWW 2026, AAAI 2027.