I am a researcher at Cohere, working group co-chair for Dynabench at MLCommons, and a final-year PhD student with the UCL NLP group under the supervision of Pontus Stenetorp and Sebastian Riedel. I have a Masters degree from the UCL Department of Computer Science and a Bachelors in Mechanical Engineering from the University of Malta.
The focus of my current research lies at the intersection of Large Language Model (LLM) robustness and Dynamic Adversarial Data Collection (DADC). I also lead the MSIN0221 Natural Language Processing module at the UCL SoM, and work closely with industry on the application of cutting-edge NLP research. Previously, I have interned at DeepMind with Po-Sen Huang and Johannes Welbl. I have also collaborated with Facebook AI Research (FAIR) under the guidance of Douwe Kiela and Robin Jia on dynamic adversarial data collection, improving model robustness and using generative assistants to improve annotation. I also worked as a Machine Learning Engineer at Bloomsbury AI.