I am a Master's student in the Institute for Computational and Mathematical Engineering (ICME) at Stanford University, specializing in Data Science. My interests lie at the intersection of machine learning, large language models, and intelligent systems, with a particular focus on building efficient, reliable, and capable AI systems.

Previously, I was a Research Fellow at Microsoft Research India in the AI4Code group, where I worked on large language models for code understanding and generation with Dr. Aditya Kanade, Dr. Nagarajan Natarajan, and Dr. Abhijeet Awasthi. My work resulted in publications at ICML, COLM, and ICLR, including work on robust adaptation of code LMs and evaluating models beyond functional correctness.

I have also worked on AI systems in both research and production settings. At Stanford, I am a Graduate Research Assistant with the Crowdsourced Democracy Team, building full-stack infrastructure for civic deliberation experiments. I am currently a Software Engineering Intern at Uber, where I work on Earner Copilot, an LLM-based conversational assistant for drivers and couriers, developing agentic capabilities for diagnosing demand and answering forecasting questions.

My recent coursework at Stanford includes Language Modeling from Scratch, Reinforcement Learning, Natural Language Processing, and Machine Learning with Graphs, complementing my broader interests in foundation models, reinforcement learning, and machine learning systems. I earned my B.Tech. in Mathematics and Computing from IIT Goa, India, in 2023. For more details about my background, see my CV. If you'd like to discuss my work or research interests, feel free to get in touch.

Experience

Uber
June 2026 - Sep 2026

-- Shipped natural-language date-query resolution in Earner Copilot, enabling drivers to ask date-grounded questions about their earnings and activity
-- Integrated 3rd-party API (Python) for real-world events data into demand-forecast answers, selecting top-3 events by attendance and masking latency
-- Built a ride-diagnostics sub-agent that runs parallel checks (earner wait time, online/on-trip state, mobility vs. delivery demand in current and nearby areas) to answer “why am I not getting requests?” with actionable diagnosis

Microsoft Research India
July 2023 - June 2025

-- Co-authored NextCoder (ICML 2025, DL4C @ ICLR 2025): designed a robust adaptation method for 7B–32B parameter code LMs across diverse code-editing tasks, achieving 10–20% absolute gains over Qwen2.5-Coder baselines.
-- Built NoFunEval (COLM 2024), a multi-language benchmark evaluating code LMs on non-functional requirements (latency, security, etc.)

IIT Goa
Jan 2023 - Apr 2023

B.Tech Project | Dr. Satyanath Bhat and Dr. Divya Padmanabhan

-- Automated process of allocating drivers optimally to Metro trains by formulating constraints in Gurobipy solver.
-- Restructured the problem using Max Flows reducing timetable preparation time from few days to a few seconds.
-- Deployed the algorithm in Bengaluru Metro Rail Corporation Limited (BMRCL).

Siemens EDA
Jun 2022 - Dec 2022

Research and Development Intern

-- Contributed to the backend of the Questa compiler in C, optimized coverage calculations to achieve a 3x improvement.
-- Designed 50+ test cases, identifying and resolving 10+ JIRA issues, significantly improving the system reliability.

Publications

NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness
Manav Singhal, Tushar Aggarwal, Abhijeet Awasthi, Nagarajan Natarajan, Aditya Kanade
COLM'24 PDF

Robust Learning of Diverse Code Edits
Tushar Aggarwal, Swayam Singh, Abhijeet Awasthi, Aditya Kanade, Nagarajan Natarajan
DL4C @ ICLR'25, ICML'25 PDF

Language Models' Factuality Depends on the Language of Inquiry
Tushar Aggarwal, Kumar Tanmay, Ayush Agrawal, Kumar Ayush, Hamid Palangi, Paul Pu Liang
Arxiv Preprint PDF

PASS: Presentation Automation for Slide Generation and Speech
Tushar Aggarwal, Aarohi Bhand
Arxiv Preprint PDF

Service
Served as a Reviewer for the ACL Conference 2024-25.
Blogs