I am a Schmidt postdoctoral fellow at the Broad Institute of MIT & Harvard. I work with Prof. Caroline Uhler at MIT.
​​

My interests are centered on probabilistic machine learning methodologies with an emphasis on structure and variation capture in high-dimensional data.

 

Concretely, my research spans three axes of variation:

​

• Manifold learning, Dimensionality Reduction & Latent Structure Discovery.

• Probabilistic Latent Variable models and Deep Generative Modelling. 

• Gaussian processes and kernel design.

 

I actively work in scientific applications of machine learning to problems in contemporary sciences like computational biology, drug-discovery and astronomy. I currently work on generative models for small molecules and the evaluation of foundational models through the lens of their representation learning capabilities.
​
I completed my PhD at the University of Cambridge (UK) in 2024. I was based at the Cavendish Laboratory (Physics) and the Computational & Biological Learning Lab at the Dept. of Engineering. During my time in Cambridge I was a Turing Scholar and a member of Christ’s College. I was awarded a G-Research PhD prize for my thesis and a Qualcomm Innovation Fellowship. 
​​
I was supervised by Prof. Carl Rasmussen and Prof. Neil Lawrence at Cambridge. I also hold a MPhil in Scientific Computing from the University of Cambridge (Distinction), an MSc in Applicable Mathematics from the LSE (Distinction). I did my undergraduation in Mathematics (major) and Economics as an external student of the Univeristy of London (LSE).​​​​