Data Scientist • Computational Epidemiologist • Health Data & Machine Learning

Dr Reju Sam John

Transforming complex data into evidence that drives decisions through |

About Me

I am a computational epidemiologist turned engineer, based in Auckland. My journey began in high-performance computing — simulating galaxy clusters on supercomputers — and has evolved through infectious disease modelling and peer-reviewed research into the cloud engineering and applied ML work I do today. The throughline is the same: rigorous thinking about complex systems, whether the system is a galaxy, an epidemic, or a production ML pipeline.

Today a university research clinic, a hospital neurology service, a health-tech company and a training institute each bring me in for the same thing: health data and models that hold up to scrutiny. I am the data scientist for the Neurogenetics Research Clinic at the University of Auckland's Centre for Brain Research, run the data behind the neurogenetics registry and biobank at Auckland City Hospital, lead engineering for a digital mental-health platform at Loffty, and lead the Data Science & AI programme at the Institute of Data. I am most engaged when the problem is genuinely hard and the stakes are real — health data, clinical informatics, any domain where the distance between data and a critical decision matters most. Whatever I am building, I try to bring the same standard: reproducible, honest, and built to last.

When I am not architecting systems or training models, you can usually find me exploring Auckland's craft beer scene, chasing the perfect cup of specialty coffee, or deep-diving into whatever complex problem has caught my attention that week.

Work Experience

Eight unbroken years of computational work, from supercomputers to hospital registries.

Current practice since 2026

Research, clinical care, health tech and teaching: four teams that rely on the same skill.

Senior Data ScientistNeurogenetics Research Clinic

Waipapa Taumata Rau | University of Auckland — Centre for Brain Research, Faculty of Medical and Health Sciences

Since Oct 2026
  • Designing and administering the central REDCap database for an international nerve ultrasound collaboration in an inherited neurological condition: electronic case report forms, repeat visits and data entry from several sites.
  • Built an auditable Python pipeline that times the vestibulo-ocular reflex for every head impulse in video head impulse test (vHIT) exports, using published onset and peak definitions, with quality-control plots, a pre-registered sensitivity analysis and within-session repeatability checks for an inherited neuropathy cohort and controls.
  • Analysis code is documented and version-controlled, with every assumption written down and signed off, so the team can rerun and check each result.
REDCapPythonSignal ProcessingNeurogeneticsReproducible Analysis

Study CoordinatorNeurogenetics Registry & Biobank

Health New Zealand | Te Whatu Ora — Department of Neurology, Auckland City Hospital

Since May 2026
  • Manage the data for the Pūnaha Io NZ Neurogenetic Registry & Biobank and related disease registries in REDCap: version-controlled data dictionaries, Python validation and migration tooling, and record linkage across projects. Department REDCap Super-User.
  • Build reproducible research pipelines in Python, including a PubMed/OMIM literature search for a scoping review and signal processing of vestibular (vHIT) recordings.
REDCapPythonClinical RegistriesRecord LinkageData Validation

Head of EngineeringCloud Architecture & Machine Learning

Loffty

Since Apr 2026
  • Lead engineering for a digital mental-health platform that screens and reports across depression, anxiety, perinatal, trauma and addiction domains. Own the AWS serverless stack (Lambda, DynamoDB, Cognito, API Gateway) and the migration of the legacy PHP/MySQL system to it.
  • Rebuilt the clinical assessment and scoring engine against DSM-5 criteria. Moved scoring parameters into versioned, immutable templates so every historical score can be reproduced. Found and fixed a result-ordering defect in how scores were combined, and hand-checked scores against clinician-approved reference outputs to the decimal before release.
  • Built privacy-preserving analytics for workplace wellbeing programmes, with aggregate-only reporting enforced at the data layer. Ran funnel and cohort analyses, such as practitioner activation and registration tracking in GA4, that shaped go-to-market decisions.
  • Set out a psychometric research roadmap covering item response theory, computerised adaptive testing, and the ethics and consent steps needed before publishing.
ReactTypeScriptAWS LambdaDynamoDBServerlessSQLPythonMachine Learning

Lead Trainer — Data Science & Generative AI

Institute of Data

Since Apr 2026
  • Lead trainer for a 25-week, part-time Data Science & AI programme delivered live online, taking learners from no programming experience to a deployed capstone project; supervise an assistant trainer.
  • Teach Python, statistics, SQL, machine learning, NLP, deep learning, generative AI and MLOps. Author teaching notebooks and maintain the course’s public GitHub repository and delivery plan.
Data ScienceGenerative AILLMsPythonTraining

Career 2018–2026

Machine Learning & Data Science Consultant

Molecular Epidemiology and Public Health Laboratory

Sep 2024 – Apr 2026 · remote
  • Analyse bat surveillance datasets and develop statistical and machine-learning models to investigate infection dynamics and transmission patterns.
  • Provide R and Python programming support to a PhD project, translating research questions into reproducible analytical workflows, including data cleaning, transformation and exploratory analysis in a Linux command-line environment.
  • Built a research assistant that answers questions from peer-reviewed publications — the Ask My Papers chat on this site.
PythonRML PipelinesData GovernanceStakeholder Communication

Postdoctoral Fellow — Data Science, Network Theory & Health Informatics

The University of Auckland

Jan 2023 – Mar 2024
  • Built and managed a longitudinal database integrating clinical records, lab results, and behavioural data with full audit-ready documentation and data quality controls.
  • Designed large-scale computational models coupling multiple data sources — from network analysis to simulation — delivering actionable insights for intervention planning.
  • Developed reproducible, version-controlled analytical workflows (Python, Linux) and communicated findings to cross-functional technical and non-technical audiences.
Database DesignData QualityNetwork AnalysisPythonLinux

Postdoctoral Fellow — Computational Epidemiologist & Health Data Scientist

Massey University

Nov 2020 – Jan 2023
  • Led end-to-end development of predictive models across 340 regions — from data acquisition and feature engineering to model validation and deployment — published as first-author in Journal of the Royal Society Interface.
  • Built scalable ETL pipelines integrating multi-source datasets (APIs, web scraping, administrative records), achieving 90% forecasting accuracy with ensemble ML models.
  • Maintained structured databases with quality control, data validation, and downstream ML-readiness. Collaborated with international cross-functional teams (NZ, USA, Europe).
ETL PipelinesEnsemble MLForecastingAPIsData Validation

Postdoctoral Fellow — Astrophysics Simulations & Computational Data Science

Inter-University Centre for Astronomy and Astrophysics (IUCAA), India

Aug 2018 – Nov 2020
  • Designed automated data processing pipelines for large-scale (1 TB+) datasets on HPC clusters; applied statistical inference and ML techniques to high-dimensional data for pattern detection and anomaly identification.
HPCData PipelinesStatistical InferenceBig DataAutomation

Visiting Fellow

Georgia Institute of Technology, Atlanta, USA

Mar 2019 – Apr 2019
  • Contributed to the development of the next-generation Enzo astrophysical simulation code, collaborating with the research team on computational methods for large-scale cosmological simulations.
HPC SimulationEnzoCosmological ModellingC

Technical Skills

Programming & Tools

Python R SQL Bash/Shell C Git/GitHub Linux LaTeX React TypeScript

AI Engineering & LLMs

RAG Pipelines LangChain ChromaDB Vector Search Embedding Models Prompt Engineering LLM APIs (Groq / OpenAI) ONNX Runtime

Machine Learning

Scikit-learn TensorFlow PyTorch Deep Learning NLP Ensemble Methods Time Series

Data Engineering

ETL Pipelines REST APIs FastAPI Data Warehousing Web Scraping Data Validation Pandas NumPy Airflow REDCap (Super-User) Record Linkage

Visualisation & Applications

Power BI (DAX) Tableau Streamlit Plotly Dash Flask Matplotlib Seaborn

Cloud & DevOps

AWS Serverless (Lambda, DynamoDB, Cognito, API Gateway) Google Cloud Render Cloudflare Pages Cloudflare Workers GitHub Actions CI/CD HPC Clusters Slurm Docker

Domain Expertise

Epidemiology Health Informatics Clinical Trials Clinical Registries & Biobanks ICH GCP R3 Health Equity Te Tiriti o Waitangi

Featured Projects

Data products, ML pipelines, and open-source research code

wx: Eight Weather Models, One Forecast

Most weather apps show one model. wx asks eight (ECMWF, GFS, ICON, UKMO, JMA, GEM, Météo-France, CMA) for the same place, headlines the median and shows how far they disagree. Works in a terminal via curl or in a browser.

TypeScriptCloudflare WorkersEnsemble Forecasts
Live Tool

Starseal: Sealed File Drops

End-to-end encrypted file sharing: files are encrypted in the browser, and the key travels after the # and never reaches the server. Each drop carries a Seal — the nine stars of Matariki at their real positions, turned by bytes of the key — so sender and recipient can confirm they hold the same drop.

Web CryptoCloudflare WorkersD1TypeScript
Live Tool

OMIM Search Tool & Reproducibility Package

A guided command-line tool for searching the OMIM API and exporting to Excel, CSV and JSON, written for clinicians without programming experience; and the auditable OMIM-to-PubMed completeness search behind a scoping review of hereditary neuropathy with auditory and vestibular involvement.

PythonOMIM APIPubMedReproducible Research
Research Tooling

ICU Respiratory Analytics — Enterprise BI Data Product

Production-grade data product: 34,000+ measurements processed through a four-gate ETL pipeline with audit logging, Power BI star-schema export, interactive Streamlit dashboard, and CI/CD via GitHub Actions with pytest validation.

PythonETLPower BICI/CDpytest

Predictive Metapopulation Model

Large-scale predictive model across 340 regions with multi-source data integration and parameter optimisation. Open-source, reproducible pipeline accompanying first-author publication.

PythonPredictive ModellingPublished

Zoonotic Dynamics Simulation

Simulation-based predictive modelling with parameter estimation and sensitivity analysis. Open-source research code accompanying peer-reviewed publication.

PythonSimulationPublished

Ask My Papers

The research assistant I build at Tasman Lab. Every way a researcher can share theirs is working on this page.

Inline chat

The chat at the top of this page, for a lab or personal site.

Try it

Floating button

Bottom right of every page. Opens the same assistant in a panel.

Badge

For a university profile or anywhere that takes a linked image.

Ask my research

QR code

For posters, slides and conference talks.

QR code that opens my research assistant

Email signature

Dr Reju Sam John Ask my research →

Selected Publications

11 peer-reviewed articles • Google Scholar • ORCID

2025

Land use change and infectious disease emergence

Rulli, M.C., … John, R.S. et al.

Reviews of Geophysics, 63, e2022RG000785

2024

High connectivity and human movement limits the impact of travel time on infectious disease transmission

John, R.S. et al.

Journal of the Royal Society Interface, 21(210)

2024

Modelling Lassa virus dynamics in West African Mastomys natalensis

John, R.S., Fatoyinbo, H.O., & Hayman, D.T.S.

Journal of the Royal Society Interface, 21(216)

2023

Identifying SARS-like coronavirus spillover risk hotspots

Muylaert, R.L. et al. (incl. John, R.S.)

Nature Communications

Nature Comms
2022

Transmission models indicate Ebola virus persistence in non-human primate populations is unlikely

Hayman, D.T.S., John, R.S., & Rohani, P.

Journal of the Royal Society Interface, 19(187)

Research Showcase

Visual summaries of selected research outputs and data products

Education & Certifications

Education

Ph.D. in Physics
Computational Modelling, Data Analysis & Simulation
Pondicherry University, India
2011 – 2018
M.Sc. in Physics
Mahatma Gandhi University, India
2006 – 2008

Certifications

Understanding Te Tiriti o Waitangi
Groundwork • Sep 2025
ICH Good Clinical Practice R3
Global Health Training Centre • Jul 2025
AWS Machine Learning Essential Training
Mar 2025
Google Cloud: Building Data Pipelines
Apr 2025
Deep Learning • NLP with Python • Ensemble Learning
Apr 2025
Power BI • SQL, Tableau, Python & Spark
2024

Get in Touch

I take on a small number of research and data engagements each year. If your team has hard health data and a decision riding on it, let's talk.

Work With Me

I build end-to-end data products — from ETL pipelines and predictive models to dashboards and APIs. 7+ years experience, PhD-qualified, with a track record of delivering measurable outcomes across cross-functional teams.

Send Me an Email

Research Collaboration?

My expertise spans computational modelling, AI evaluation, predictive analytics, and health informatics. I'm eager to collaborate on impactful, data-driven research across domains.

Propose a Collaboration