Case study
A practical build spanning Python, Mathematical Modelling, SciPy, NumPy, Docker.
Overview
Productionised ML models for epidemic modelling in remote, low-resource environments for Médecins Sans Frontières (MSF). This pro bono engagement applied mathematical epidemiology expertise to real-world public health challenges, bridging the gap between research models and deployable tools for field teams operating with limited connectivity.
Context
MSF needed epidemic models that could run in environments with limited or no internet connectivity. Research-grade models existed but were not suitable for field deployment — they required specific runtime environments, large datasets, and continuous connectivity.
Architecture
Adapted mathematical epidemiology models (building on my MSc research in Mathematical Biology) for offline-first deployment. Containerised the models for portable execution and designed lightweight data input interfaces suitable for field teams.
Outcome
Delivered production-ready epidemic modelling tools suitable for field deployment in remote environments. The engagement demonstrated that mathematical rigour and production engineering can combine to serve humanitarian goals.
Retrospective
Working with MSF reinforced that the hardest engineering problems are often constraints-driven, not algorithm-driven. The offline-first requirement shaped every architectural decision.
More projects
Led architecture and delivery of a production-grade RAG chatbot for John Lewis Partnership's internal workforce — from first …
Defined and delivered JUMO's internal ML platform from first principles — a config-driven orchestration layer that scaled model …
Designed and built a real-time model monitoring system at JUMO that reduced data anomaly detection time from weeks …
If you need secure GenAI delivery, RAG engineering, MLOps automation, or production ML systems support, feel free to get in touch.