I am a researcher at Cohere currently leading the post-training team (Command), and working group co-chair for Dynabench at MLCommons. My PhD, under the supervision of Pontus Stenetorp and Sebastian Riedel with the UCL NLP group focused on the adversarial robustness of Language Models with humans and models in the loop. 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 research lies at the intersection of Large Language Model (LLM) robustness and reasoning. Previously, I developed and taught the MSIN0221 Natural Language Processing module at the UCL SoM. I 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.
