Hi, I’m Nalin.
I’m a PhD student in Computer Science at the University of Illinois Urbana-Champaign.
My research focuses on building robust, verifiable and trustworthy AI systems. I am studying large language models through the lens of formal methods, and I belive we should use formal tools and symbolic techniques to understand and provide guarantees on model behavior. I am currently working towards deterministic verification and robustness of large language models. I have also worked on Machine Learning for Software Engineering (ML4SE) — including automated program repair, code generation, and LLM-based coding agents for complex software development tasks. Broadly, I’m excited about bridging formal methods, machine learning, and software engineering to create AI systems that are both powerful and trustworthy.
Education and Experience
PhD in Computer Science at University of Illinois Urbana-Champaign advised by Gagandeep Singh — 2025 – Present
Research Fellow at Microsoft Research India with Dr. Sriram Rajamani, Dr. Aditya Kanade, and Dr. Nagarajan Natarajan — 2023 – 2025
Data and Applied Research Intern at Microsoft IDC, Hyderabad with Ram Shankar — Summer 2022
B.Tech in Computer Science and Engineering at Indian Institute of Technology Delhi, Undergraduate thesis with Prof. Sorav Bansal — 2019 – 2023
Publications
A full list lives on the Publications page.
Scaling Deterministic LLM Verification to Prompt Spaces
Nalin Wadhwa, Brian Kim, David Shu Cheng, Isha Chaudhary, Avaljot Singh, Gagandeep Singh
Under review
[Preprint]
BEAVER: An Efficient Deterministic LLM Verifier
Nalin Wadhwa*, Tarun Suresh*, Debangshu Banerjee, Gagandeep Singh
Oral, VerifAI Workshop at ICLR 2026
[Project page] [arXiv] [GitHub]
Code Researcher: Deep Research Agent for Large Systems Code and Commit History
Ramneet Singh*, Sathvik Joel*, Abhav Mehrotra, Nalin Wadhwa, Ramakrishna B Bairi, Aditya Kanade, Nagarajan Natarajan
[Project page] [arXiv]
MASAI: Modular Architecture for Software-engineering AI Agents
Nalin Wadhwa*, Daman Arora*, Atharv Sonwane*, Abhav Mehrotra, Saiteja Utpala, Ramakrishna B Bairi, Aditya Kanade, Nagarajan Natarajan
NeurIPS 2024 Workshop on Open-World Agents
[Project page] [arXiv]
CORE: Resolving Code Quality Issues Using LLMs
Nalin Wadhwa, Jui Pradhan, Atharv Sonwane, Surya Prakash Sahu, Nagarajan Natarajan, Aditya Kanade, Suresh Parthasarathy, Sriram Rajamani
Proceedings of the ACM on Software Engineering, FSE 2024
[ACM] [arXiv]
* denotes equal contribution
Talks
Formal Guarantees for Frontier AI Systems — NeurIPS 2026 Tutorial, Sydney (co-presented with Gagandeep Singh and Isha Chaudhary) — Dec. 2026
BEAVER: An Efficient Deterministic LLM Verifier - NSF PPoSS Weekly Seminar, University of Illinois Urbana-Champaign — Oct. 2026
Service
Reviewer, International Conference on Machine Learning (ICML) 2026 — Gold Reviewer Award, awarded to top reviewers at ICML 2026
Teaching and Mentoring
Teaching Assistant, CS 521: Advanced Topics in Formal Methods — Trustworthy AI, UIUC — Fall 2026
Undergraduate Research Mentoring — I mentor undergraduate researchers at UIUC on projects in formal verification of language models.
Other Interests
Outside of research, I greatly enjoy reading fiction, philosophy, and everything in between. I also enjoy cooking, making electronic music, and can play almost all racket sports.
I grew up in various cities across India, but my roots are in Delhi.
Contact
The best way to reach me is by .