EST. — Data Scientist in London
Chaeyoon
Kim.
Data Scientist at NHS England · Certified AI Ethicist · London
01 — About
Working at the edge of data and AI.
I'm a Data Scientist and Certified AI Ethicist with a passion for AI engineering. After 6.5 years in semiconductor engineering at Samsung Electronics, I've spent about five years in data science across the UK National Health Service (NHS).
Past community roles: LangChain Global Ambassador (2025–26) · UK–Korea Global Health Forum working group · Professional Mentor at City St George's and the University of Greenwich · PyCon UK volunteer.
View full CV ↗02 — Projects
Selected work.
NLP, Text & QA
NoteGuard — Trust Layer for Clinical AI
LangGraph agent (Gemini + Tavily) that de-identifies NHS clinical free-text before any model or tool sees it — assert_clean() raises if a single identifier survives. Real names are restored only in the clinician-facing answer, alongside a measured residual-PII trust score.
2nd Place
NHS Career Coach
Multilingual AI career coach helping students and graduates navigate 350+ NHS career pathways. Retrieves and cites Health Education England careers content and adapts its communication to different user personas, built by a seven-person NHS England and Microsoft team over a two-day hackathon for the NHS Website Services team. Azure AI Foundry with a Streamlit front end, plus the team's prompting and meta-prompting strategy, validation process and personas.
1st Place
Semantic Answer Type Prediction
MSc dissertation submitted to the SMART 2021 shared task at the International Semantic Web Conference. Ranked 1st for classifying the expected answer type — entity, literal, or boolean — from natural-language questions over a knowledge graph.
↗
AI Engineering & ML
4th Place
Endo Loop — At-home Endometriosis Pattern Journal
Non-diagnostic, at-home pattern journal for endometriosis and chronic pelvic pain. Voice or manual daily check-ins are validated with Pydantic, merged with wearable signals (HRV, resting heart rate, sleep, skin temperature), and run through a deterministic pattern engine with conservative safety rules; an optional LLM only phrases explanations, never decides a pattern. Produces a clinician-ready summary with patient-controlled sharing. FastAPI + React.
NHS Policy Navigator
Adaptive retrieval agent over the NHS 10-Year Health Plan, built in London. Uses agentic RAG to answer nuanced policy questions with source attribution.
Community Pharmacy Workforce Projection
Workforce projection model for NHS community pharmacy, built on open data. Projects the supply of pharmacists and pharmacy technicians across baseline, optimistic, and pessimistic scenarios, using compound annual growth rates from GPhC registers and the Community Pharmacy Workforce Survey.
↗
Pharmacy Analysis with Open Data
Python package (published to PyPI) for analysing NHS pharmacy open data at national and regional scale. Covers supervision and staffing across 10,000+ pharmacies, with Cohere-powered accessibility prediction and a Google Maps pharmacy finder. Vibe-coded with Cursor.
Reducing Missed NHS Appointments
ML solution to cut the cost and waitlist impact of non-attended hospital appointments, developed for a hackathon challenge set by the No. 10 data science team.
↗
More projects
Korean AI-Tone Detector — Slack Advisory
Scores Korean blog posts for AI-generated-sounding prose and posts an advisory to Slack. Re-implements linguistic features from KatFishNet (ACL 2025) — comma usage, translation-ese and double-passive patterns, POS n-gram diversity and word spacing — with kiwipiepy, and lists every feature that fired so a human can contest the flag. Advisory only, never a verdict.
Bilingual To-Do — Korean & English
My seed idea for a bilingual Korean/English Kanban: a child's typed, spoken, or tapped message is routed to a tool that updates the board — a tool-calling agent sandbox on the route → dispatch pattern, with a PIN-gated parent mode and cards that conjugate by column to teach tense. This repo is the Korean-readable origin; with KUITA collaborators it grew into the live togethertodo app for pre-literate toddlers learning alongside their mums.
Getting Started with Makaton — AAC Choice Board
Digital symbol-based choice board for non-verbal and emerging-verbal pupils in UK SEN schools. React 18 + Supabase, optimised for iPad. Predictive card suggestions via Markov chain and Thompson-sampling bandit — no runtime LLM dependency. GDPR-compliant with multi-source AAC symbol fallback chain.
↗