Experience &
education.

Experience

• Apr 2024 — Present

  Data Scientist

  NHS England · London, UK

  • Redesigned the CT1 training-place allocation methodology from a weighted multi-criteria model into a rule-based model in Python and Excel, presenting outputs via Tableau to inform prioritisation for under-doctored deaneries during 2024 BMA industrial-action negotiations.
  • Lead Developer for the 10-Year Workforce Plan under NHSE's Business Critical Model governance: coordinating with UDAL Data Engineers on secure Azure Data Lake environments and building pipelines in SQL, Python and PySpark; co-led the migration of legacy PySpark pipelines off deprecated DBFS onto Entra-secured Data Lake containers, and coordinated Windows 11 migration testing to protect BCM continuity.
  • Led the transition of legacy Excel workforce models into reproducible Python and PySpark pipelines, addressing National Audit Office recommendations through documented assumptions, strengthened data lineage and peer-reviewed Git version control — cutting model runtime by around half.
  • As Community Pharmacy modelling workstream lead, coordinated a dozen stakeholder groups — including pharmacy Deans and Chief Pharmaceutical Officers — into a single delivery scope, launched a Pythonised supply-and-demand model within six months and secured the model SRO's approval despite late changes to baseline and counterfactual assumptions.
  • Designed an NLTK-based sentiment-analysis pipeline for the Reporting, Insights, Publications and Transparency programme and contributed to a paper on insights maturity for the CEO's office and Board; presented 10YWP model components to the External Scrutiny Panel and the national consultation on Community Pharmacy workforce interventions.
  • Delivered Python, PySpark and Git training and onboarding for analysts and new data scientists, promoting coding best practice across the modelling team.
• Jun 2022 — Mar 2024

  Junior Data Scientist

  Health Education England · London, UK

  • Maintained a pythonised geo-spatial analysis and produced Tableau dashboards analysing clinical placement capacity, workforce supply trends and geographic demand across 65 medical specialties for the HEE Board's tariff-funding review, advising medical Deans on redistributing specialty training posts and informing NHSE's recommendations to the Office for Students on new dental school places.
  • Supported R modelling to predict complex birth deliveries for maternity service planning, using source data from RCOG statisticians.
  • Collaborated with Data Engineering and Product teams on Jira / Agile to manage project timelines.
• Apr 2022 — Jun 2022

  Data Manager

  UCL Great Ormond Street Institute of Child Health · London, UK

  • Worked with bioinformaticians and statisticians on the GSK Sotrovimab Covid-19 study, cleaning and transforming lab data.
  • Designed a MySQL server for secure data transfers from study entry points.

Selected Projects

• Strategic Planning

  10-Year Workforce Plan modelling

  NHS England · DHSC

  • Refreshing the NHS Long-Term Workforce Plan modelling (published Jun 2022) with a multidisciplinary group, incorporating National Audit Office feedback.
• AI & ML

  LLM & machine learning prototypes

  NHS · Hackathons & conferences

  • Pharmacy First agent — LLM-powered analysis of NHS pharmacy operations, open-sourced and presented at PyConUK, NHS RPySOC and HACA 2025.
  • NHS Policy Navigator — adaptive Retrieval-Augmented Generation pipeline over the published 10-Year Health Plan and public NHS news feeds, refined with a working group through a spec-driven development cycle at near-zero infrastructure cost.
  • Reducing missed NHS appointments — ML solution for a No. 10 Downing Street data science hackathon, targeting waitlist cost.
  • NHS Career Coach — POC chatbot on Microsoft AI Studio; 2nd place hackathon, showing how LLMs can support candidates.
  • OPEL prediction — ML models on the NHS Federated Data Platform during a Palantir & KPMG hackathon.
• Teaching & Outreach

  AI Engineering training programme

  Undergraduates to NHS analysts & clinicians

  • Designed and delivered a training programme teaching reproducible software engineering, responsible AI and governance principles using open-source NHS datasets and public repositories; accepted as a peer-reviewed oral presentation in computer science education.
• Research

  Textbook contribution

  Foundations of Programming, Statistics, and ML for Business Analytics

  • Developed R and Python conversion code for the English edition (Apr 2023); co-authored the Korean translated edition (Feb 2025).

Education

• 2020 — 2021

  MSc Data Science — Distinction

  City St George's, University of London

  • Awarded 1st rank for the System for the Semantic Answer Type Prediction Task; presented at the International Semantic Web Conference (ISWC), October 2021.
• 2018 — 2020

  PgCert Data Analytics

  University of Sheffield

  • Modules: Computer Security and Forensics, Machine Learning and Adaptive Intelligence, Statistical Data Science in R.
• 2007 — 2011

  BSc Electronic Engineering

  Kyungpook National University · Daegu, South Korea

  • Modules: Electronic Engineering Lab (MATLAB), Calculus, Numerical Analysis.

Community & Volunteering

• 2025 —

  LangChain Ambassador

  London

  • Hosting technical meetups and organising a hackathon in central London.
• Ongoing

  UK–Korea Global Health Forum working group

  London School of Hygiene & Tropical Medicine

  • Organising a conference with senior researchers at LSHTM.
• Ongoing

  Professional Mentor

  University of Greenwich · City St George's

  • Supporting early career interview preparation.