I am a Postdoctoral Fellow in Software Engineering at the University of British Columbia under the supervision of Prof. Ali Mesbah. I am fortunate to be part of the SALT lab. My research is in software engineering, with emphasis on AI-driven software analysis, code repair, and software testing. My research aims to understand the role of context for code-related tasks with large language models.

My work has been recognized by the ACM SIGSOFT Distinguished Paper Award at ASE 2025, reflecting the broader impact and rigor of my research contributions. My research has received over 500 citations (h-index: 11), including CEDAR which has been cited more than 300 times and featured in an article by IBM on few-shot prompting.

Beyond research: I aspire to work at the intersection of academia and industry to build novel solutions, tools, and techniques that directly benefit software practitioners. I believe the boundary between academic research and industrial practice in software engineering will continue to blur, and I want to play an active role in fostering this bidirectional flow of knowledge to ensure both scientific advancement and practical impact. I am also interested in how technology might shape the trajectory of our civilization and in advancing AI research that aligns with societal benefit.

Broadening access: A major barrier for aspiring researchers from the Global South is often not ability but access. Access to mentorship, networks, and the tacit norms that shape academic research. My goal as a mentor is to make these tacit norms explicit. I currently mentor pre-doctoral fellows through the Fatima Fellowship.

Highlights & Selected Publications

ACM SIGSOFT Distinguished Paper Award at ASE 2025

Issue2Test: Generating Reproducing Test Cases from Issue Reports, ICSE 2026

Panta: LLM Test Generation via Iterative Hybrid Program Analysis, ICSE 2026

Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair, ASE 2025

FLAKIDOCK: Dockerfile Flakiness Characterization and Repair, ICSE 2025

AUTOE2E: A Feature-Based Approach to Generating Comprehensive End-to-End Tests, ICSE 2025

CEDAR: Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning, ICSE 2023