Curriculum Vitae
I study how to make deployed AI systems reliable across long conversations, shifting user intent, and real-world constraints. My work spans agent post-training, evaluations designed with domain experts, instruction following, and test-time monitoring, with applications in reproductive health, wildlife conservation, and road safety.
Research focus
- Post-training environments that teach agents to clarify intent, recover, abstain, or delegate.
- Contextual evaluations built with domain experts rather than proxy metrics alone.
- Understanding and improving agents' instruction-following behavior.
- Monitoring deployed systems at test time.
Research and engineering impact
- HAMS: Automated driver's-license testing deployed across India; more than 440,000 candidates assessed.
- PATHFinder: Conversational agent being deployed with clinicians and patients for personalized prenatal care planning at the University of Michigan.
- Elephant Re-ID: Computer vision models being deployed for elephant re-identification in Botswana.
- SmartCampus: Co-founded a campus payments platform that processed INR 25 million at 1,000 active users per minute.
Technical skills
Python, C++, JavaScript; PyTorch, JAX, SkyRL, verl.
Education
-
University of Michigan, Ann Arbor
2023 – present (expected Dec 2027)Ph.D. Candidate, M.S. in Computer Science and Engineering
GPA: 4.0. Advised by Prof. Elizabeth Bondi-Kelly.
-
BITS Pilani, Hyderabad Campus
2016 – 2020B.E. in Electronics and Communication Engineering
Research experience
-
Microsoft Research Redmond, AI Frontiers
May – Aug 2025Research Intern
Applied multi-turn reinforcement learning (GRPO) to help LLM agents clarify intent and recover from errors across extended episodes, and built evaluation harnesses for multi-turn performance. Advised by Hussein Mozannar, Adam Fourney, Gagan Bansal, Saleema Amershi, and Eric Horvitz.
-
Microsoft Research India
Jun 2022 – Jun 2023Research Fellow
Built runtime prompt, LLM, and embedding-model selection strategies, plus multilingual evaluation and retrieval components for VeLLM. Evaluated across 18 languages. Also developed Chanakya's contextual-bandit approach to runtime accuracy and latency tradeoffs. Advised by Dr. Akshay Nambi, Tanuja Ganu, and Dr. Venkat Padmanabhan.
-
Microsoft Research India
Jun 2021 – Jun 2022Societal Impact through Cloud and AI Fellow
Developed visual SLAM, object detection, and trajectory analysis for HAMS automated driver's-license testing. Advised by Dr. Akshay Nambi, Tanuja Ganu, and Dr. Venkat Padmanabhan.
Publications and working papers
-
MATTER-LC: Multimodal Agentic Task Orchestration for Transforming Evidence into Source-Auditable Records in Landslide-Loss Curation
Working paper
-
RELIANCE: Curating and Evaluating Reproductive Health Information on Social Media
KDD 2026 · Datasets and Benchmarks Track
-
PATHFinder Agent for Tailored Prenatal Care
Interactive Health 2026
-
"Where is this coming from?" Uncovering Trustworthiness Ideals in AI-powered Peripartum Information Seeking
FAccT 2026
-
SEEK-CBM: Editable and Interpretable Retrieval for Elephant Re-Identification
CV4Animals @ CVPR 2026
-
Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
COLING 2025 · Oral
-
Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval
IJCAI 2024 · Human-Centered AI track · <5% accept
-
Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception
NeurIPS 2023
Awards and recognition
- 2025 Exceptional rating, Ph.D. preliminary exam (advancement to candidacy)
- 2024 2nd place, Google × MHacks hackathon (USD 1,500); featured by labs.google
- 2023 Selected for the Harvard/MIT HAIST/MAIA introductory fellowship on AI safety
- 2022–2024 VeLLM cited by Satya Nadella and covered in the Times of India; HAMS covered in the Punjab News Express
Service
-
Conference reviewing
NeurIPS 2024–2026, KDD 2026, IJCAI 2025, ICML 2025, AAMAS 2025, ICLR 2025
-
Workshop reviewing
CVPR 2024, NeurIPS 2023, ACL 2026