Henry Wilde

Summary

I am a thoughtful, ethically minded scientist who enjoys building useful things. My work includes public health data science, machine learning, and privacy-preserving engineering. I take pride in learning new tools quickly and applying them to solve real problems.

Core skills

Python data science stack, uv Version control git, GitHub, Azure DevOps Platforming AWS, GCP, Azure, Docker Automated testing pytest, hypothesis, unittest.mock, GitHub Actions, Azure Pipelines Documentation Diátaxis, Wikis, GitHub Pages, Markdown, LaTeX

Employment

Oct 2024 - present Research engineer  Creditsafe

• Founding member of the R&D team, building tools to improve core products and business processes.
• Technical owner of projects for the Data directorate and Swedish office using technologies including LLMs, knowledge graphs, and data synthesis.
• Mentor to junior engineers, helping to foster a culture of software sustainability and rigour.

LLMs Gemini, OpenAI Knowledge graphs Neo4j, TypeDB

Jun 2024 - Oct 2024 Data scientist  Dŵr Cymru Welsh Water

• Collaborated on analytics to support data-driven operational decisions.
• Applied survival analysis to enable proactive maintenance of critical infrastructure.
• Improved software engineering practices through code review and automated testing.

May 2022 - Jun 2024 Data scientist  Data Science Campus, Office for National Statistics

• Led development of an LLM-based reader to summarise ONS activity in parliamentary debates, generating significant cost savings.
• Core developer of the privacy-preserving record linkage toolkit, including its secure computation architecture on GCP.
• Mentored a team of apprentices to build a Python interface to the 2021 Census API for England and Wales.
• Technical lead for producing high-fidelity synthetic census microdata using distributed computing and differential privacy.

LLMs Gemini, OpenAI, LangChain Publishing Quarto, Streamlit Distributed computation Dask, PySpark, Google BigQuery

Feb 2021 - May 2022 Research associate  Water Research Institute, Cardiff University

• Designed and implemented software infrastructure for the Welsh Government wastewater surveillance programme.
• Built reproducible R-based ETL pipelines for biochemical data within one month of self-learning R.
• Developed two core models for monitoring COVID-19 prevalence: a hierarchical GAM for case prediction and a Bayesian dilution model.
• Findings directly informed Welsh Government pandemic policy.

R tidyverse, mgcv, Shiny, RStan, RMarkdown LIMS

2019-2020 Volunteer consultant  School of Biosciences, Cardiff University

• Commissioned to improve the school’s dissertation allocation process.
• Built a programmatic framework using my open-source Python matching library.
• Cut allocation time from a week to seconds while guaranteeing fairness.

Dissertation supervisor  School of Mathematics, Cardiff University

• Co-supervised an MMORS project on Folk Theorems in game theory.
• Mentored the student on sustainable research software development and report writing.

2017-2021 PhD studentship teaching  School of Mathematics, Cardiff University

• Delivered seminars in statistics and computing; supported hackathons and the university maths support service.
• Founded an Advanced Python Workshop and code clinic for my peers.
• Mentored a high-school student during a Nuffield Research Placement.

Education

2017-2021 PhD Applied Statistics, Operational Research and Data Analytics  School of Mathematics, Cardiff University

• Thesis on the ethical and rigorous use of machine learning in healthcare.
• Proposed new perspectives for algorithm evaluation via data synthesis, and fair clustering.
• Delivered actionable insights to co-funders using administrative healthcare data.
• Accompanied by a suite of open-source research software packages.

2014-2017 BSc Mathematics (First Class Honours)  School of Mathematics, Cardiff University

• Explored operational research, computing, and pure mathematics.
• Achieved perfect scores in two projects: A&E simulation and iterated Prisoner’s Dilemma strategy analysis.

Publications

Full list available on Google Scholar.

Thesis

2021 Wilde, H. New methods for algorithm evaluation and cluster initialisation with applications to healthcare. Cardiff University. PDF. GitHub repository.

Journals

2022 Wilde, H., et al. Accounting for dilution of SARS-CoV-2 in wastewater samples using physico-chemical markers. Water, 14(18):2885. DOI:10.3390/w14182885

2020 Wilde, H., Knight, V. and Gillard, J. Matching: a Python library for solving matching games. Journal of Open Source Software, 5(48):2169. DOI:10.21105/joss.02169

Awards

2022-2024 Reward and Recognition  Office for National Statistics

• Eight awards across all three bands, including a sustained excellence award for synthetic data work.
• Recognised for accessible technical talks, surge-work contributions, and promoting sustainable software practice.

2022 PETs Hackathon  United Nations PET Lab

• Finished third out of 200 international teams
• Predicted hidden characteristics of Kenyan refugee households using differential privacy within a secure enclave.

Interests

Cooking

Former chef in fine dining and gastropub kitchens; cooking for friends and family remains my dearest pastime.

Cycling

Restored a vintage steel-frame touring bike during the pandemic and taught myself bike mechanics.

D & D

Game master for a long-running homebrew campaign with my three brothers; lifelong lover of fantasy and speculative fiction.