I'm a data scientist / machine learning engineer with a background in computational / quantum physics. I write loads of python and typescript, and a little bit of everything else.
I like working on hard R&D problems involving computer vision, natural language processing, graph theory, representation learning, recommendation systems, and information retrieval.
I love turning those research projects into end-to-end pipelines and services which help people in the real world.
Building the next generation of search and discovery on wellcomecollection.org, including experiments with knowledge graphs, multi-modal search, and semantic search
Prototyping and productionising computer vision pipelines, novel NLP models, and core search algorithms to help researchers find things on wellcomecollection.org.
Produced ML-heavy analyses of huge datasets, distilling visitors' motivations, expectations, and needs when visiting the museum online and IRL.
Built a matching/recommendation system for an app with hundreds of thousands of users around the world.
MSci Physics, 2:1
Thesis: Correlations between water fragments on silicon
pytorch, scikit-learn, tensorflow, wandb
jupyter, pandas, numpy, scipy, matplotlib, spacy, neo4j, networkx, elasticsearch, pyspark, SQL
AWS, terraform, docker, git, github actions, vercel, netlify, heroku, supabase
I try to share what I've learned through blog posts, reusable code, and/or talks at conferences and universities.
I'm a supervisor for UCL's Data Science for Cultural Heritage MSc course. I've also mentored and advised first-time conference speakers, artists, researchers in industry and academia, grant funding applicants, and students all the way from GCSE to PhD.
I've built a lot of open source tools, sites, and services outside of work to sharpen my own development skills and experiment with new technologies.
I like swimming outdoors, especially through the winter. I've been cycling in London for ten years and I've only been hit by four cabs.