Secured an OpenAI in-kind research grant providing frontier AI models and research tools to advance my research on trustworthy and efficient AI-assisted software engineering.

Independently lead studies of AI coding agents’ trustworthiness with partners including BT, Diffblue, and GoCodeGreen, producing research recognised by the MSR 2026 Distinguished Challenge Paper Award.

Co-designed and led LLM-based code optimisation research, delivering the two-year programme in 18 months, producing ASE 2025 and SSBSE 2025 publications, and contributing to TurinTech AI’s Series B funding.

Recognised for insightful, constructive, and thorough reviews that supported the quality of the research track programme.

Selected from 60+ submissions; recognised for empirical rigour in studying the trustworthiness of AI coding agents at scale.

Recognised for exceptional review quality in the shadow programme committee.

Led a 7-member international team to the highest-scoring submission in the GenAI optimisation challenge.

Sole recipient from 14 global candidates; recognises the most outstanding PhD dissertation in computer performance evaluation worldwide.