I am a Research Assistant at the London School of Hygiene & Tropical Medicine, where I apply natural language processing (NLP) techniques to electronic health records. I hold a PhD from UCL, where my research developed an NLP pipeline for extracting structured information from unstructured text corpora, combining feature extraction, word embeddings, and clustering methods. I program in both Python and R, using libraries for text processing, machine learning, and visualisation. I have experience working with embedding models, as well as large language models.
Affiliations
Teaching
I have three years' experience as a teaching assistant at UCL, supporting master's students in Quantitative Methods (SQL, hypothesis testing, regression, clustering, classification, and linear programming) and Data Science for Spatial Systems (supervised learning, tree-based methods, neural networks, panel regression, and spatial clustering). I have also mentored at data dives at King's College London.
