I’m currently a Florence Nightingale Bicentenary Fellow at the University of Oxford in the Department of Statistics. Prior to this, I was a Postdoctoral Scholar in the Department of Electrical and Computer Engineering at the University of California, Los Angeles (UCLA) and, before that, I completed my DPhil here in the Department, supervised by Charlotte Deane.

My research develops and applies novel machine learning methods to challenges in healthcare, medicine, and drug discovery. 

Methodologically, my work spans both predictive and generative methods, explainable AI, feature selection, causal inference, and learning from unlabelled data. From an application perspective, I am currently particularly interested in structure-based drug design.

Please see my Google Scholar page for an up-to-date list of publications.

I am a PhD student in the StatML CDT program, working with Professor Chris Holmes since late 2020. During my PhD, I have interned as a Research Scientist at Google Research, where I developed a concept-based interpretability framework, and at IBM Research, where I created an interpretable balancing method to identify local natural experiments. Prior to my PhD, I earned an MSc in Applied Mathematics from Ecole Centrale Paris and an MSc in Medical Statistics from the London School of Hygiene and Tropical Medicine.

My PhD research is centered on AI Safety, with a focus on explainability, causal inference, and robustness. I aim to develop analytical methods that are solution-driven and applicable to real-world problems. Recently, I have been exploring topics related to Large Language Model (LLM) Alignment and Interpretability, particularly in the area of Mechanistic Interpretability.