cv

Research Intern

Microsoft Research

Developed an ontology-grounded retrieval augmented generation method for effective and efficient domain adaptation (submitted to EMNLP 2025).

• Retrieval-augmented Generation
• Domain Adaptation
• Hypergraph

Research Intern

Visa Research

Developed a plug-and-play method to classify nodes using a personalized scope of its local neighborhood. Experiments show improved robustness, interpretability, and heterophily performance (accepted at TMLR 2025).

• Interpretability
• Graph Neural Networks

Applied Scientist Intern

Amazon Science

Developed an automatic prompt-tuning method to tune class definitions that enhances zero-shot classification of textual data (submitted to internal AMLC workshop).

• Large language models
• Classification

Founding Member

Tensor Dynamics Pvt. Ltd.

Developed initial code-base for a green-tech startup to provide reliable solar energy forecasts. Forecasting models deployed by Load Dispatch Centre to monitor over 20 solar stations across India

• Forecasting
• Renewable Energy

Ph.D.

Georgia Institute of Technology

Reliability and controllability of ML models for structured data

B.Tech.

Indian Institute of Technology, Delhi

Adversarial attacks on Graph Neural Networks

Suresh Chandra Memorial Trust Award

Indian Institute of Technology, Delhi

Best undergraduate thesis in the CSE department

Summer Undergraduate Research Award

Indian Institute of Technology, Delhi

Credible research in the summers