Healthcare & Digital Health
Research and analytics workflows supporting rehabilitation, health data and clinical-facing digital products.
I’m James
I’m a UK-based Data Engineer with 3+ years of experience across data engineering, analytics and applied AI. I build reliable pipelines, cloud data workflows and analytics-ready datasets using Python, SQL and modern data tooling, with a strong focus on data quality, maintainability and making information useful for the people who depend on it.
3+
Years of Data Experience
32+
Public GitHub Repositories
3
Applied Research Projects
85%
MSc Big Data Analytics
MSc Big Data AnalyticsDistinction · University of Derby
Data EngineeringPython · SQL · Cloud · BI
Applied ResearchDigital Health · NLP · Analytics
Domains I’ve Built Data Solutions For
Government & Public Sector
NLP, consultation analytics and structured data workflows for public-service decision support.
FinTech & Financial Data
Customer-review, transaction and product analytics focused on behaviour, trends and decision-ready insight.
Real Estate & Property
ETL workflows for property data, structured analysis and reproducible reporting.
Customer & Product Analytics
Turning behavioural and feedback data into reusable metrics, themes and product signals.
Retail & Commerce
Sales, profitability and customer-data pipelines supporting BI and operational reporting.
Education & Research
Research-oriented data workflows, experimentation and reproducible analytical outputs.
Business Intelligence
Curated datasets, dimensional models and dashboards built for consistent management reporting.
How I Build Data Systems
A practical workflow from requirements and raw sources to tested, analytics-ready data products.
01
Understand the Data Problem
Clarify the business question, source systems, users, grain, constraints and what a trustworthy output should look like.
02
Ingest & Model
Design the ingestion path, clean and standardise the data, then model it around the analytical or operational use case.
03
Test & Orchestrate
Add validation, reproducible transformations, automation and monitoring so the workflow is dependable rather than just functional.
04
Serve & Improve
Publish data to the right warehouse, BI or application layer, observe usage and refine the system as requirements evolve.
Education & Applied Data Work
University of Derby
MSc Big Data Analytics
Distinction · 85% overall. Dissertation focused on trust, ethics and governance in generative AI for medical imaging.
Bowen University
BSc Computer Science & Information Technology
2:1 degree covering computing foundations, software development and information systems.
University of Derby
AI & Digital Health Research
Contributed to AI-DRA, a rehabilitation prototype combining computer vision, structured session data and accessible user feedback.
Public-Sector NLP Research
Consultation Analytics
Built NLP workflows for classifying, summarising and structuring consultation responses for analysis and decision support.
Coming soon
Data Engineering Toolkit
Additional Learning
Selected data engineering, analytics, governance and product-design learning that strengthens how I build reliable data systems.
Elsewhere on the web
Engineering, writing and design profiles
A few places where I publish technical writing, share experiments and document product or interface work.
LATEST WRITING
Notes on data engineering, analytics, AI and the decisions behind reliable data products.
Why Data Quality Should Be Designed Into the Pipeline, Not Added Later
Designing BI Dashboards That Help People Decide, Not Just Look
Designing BI Dashboards That Help People Decide, Not Just Look
What I Learned Building an AI Rehabilitation Prototype for Stroke Support
What I Learned Building an AI Rehabilitation Prototype for Stroke Support
Medallion Architecture Is Useful, But It Is Not the Point
Medallion Architecture Is Useful, But It Is Not the Point
Need someone who can turn raw data into reliable, decision-ready systems?
Let’s Talk ↗More about me
Two things that keep me curious outside day-to-day project work.