Data Scientist

Summary

Join ZOE, a leading science and nutrition company, as a Data Scientist and partner with world-class nutrition scientists. You will transform cutting-edge research into robust scoring algorithms and science-driven features, building ML/AI models using extensive member data to improve user experience and health outcomes. This role involves engineering bespoke models, validating them rigorously, and delivering production-ready code. You will collaborate with scientists, engineers, and product teams, prioritizing speed and iteration in a startup environment. The position is based within the Scoring team, a cross-functional group focused on research and product development. You will be working in a remote-first environment with a flexible work schedule and a comprehensive benefits package.

Requirements

• 3+ years of professional experience in data science, ML engineering, or quantitative research
• A degree in a quantitative field (e.g., Applied Maths, Physics, Biomedical Engineering, Statistics, Computer Science)
• Solid grasp of machine learning (e.g. training and evaluating standard models) and statistical techniques (e.g. running hypothesis testing)
• Experienced in contributing to production-level Python codebases, developing new components and features, writing moderately complex SQL queries, and using Git for version control
• Experience turning domain knowledge (rules, heuristics, scientific findings) into engineered model logic
• A track record of shipping production code and collaborating in cross-functional, fast-paced environments
• Comfort using AI tools to enhance day-to-day productivity—from IDEs with AI assistants to prompt engineering
• Strong communication and collaboration skills—from delivering clear presentations to stakeholders to conducting deep-dive code reviews and working collaboratively across functions
• Must have a passion for nutrition, health tech, biology, or a strong desire to dive in and learn quickly
• A commitment to our #ActFast value: optimise for reversible decisions, take smart risks, and move quickly with imperfect data

Responsibilities

• Design, iterate, and deploy scoring algorithms for foods, diets, metabolic responses, and microbiome profiles
• Translate expert food statements (e.g., ‘High-glycaemic foods raise blood glucose responses’) into model features and Python functions
• Build, test, and maintain clean, production-ready code in Python (pandas, NumPy, scikit-learn), and SQL/DBT/BigQuery/Airflow
• Build ML/AI models to improve food coverage and categorisation, ingredients extraction, food recommendations, and more
• Design validation frameworks that blend scientific rigour (e.g., hold-out tests, bootstrapping, sensitivity analyses) with pragmatic speed
• Partner with engineers to shape data contracts and ensure pipelines deliver the granularity, latency, and quality your models require
• Present results using decks, dashboards, or Looms to support data-driven product decisions
• Take full ownership of your work, brining entrepreneurial spirit and work proactively
• Champion our scientific yet agile approach: start with a hypothesis, seek evidence, and iterate fast

Preferred Qualifications

• Experience with causal inference and advanced statistical modelling
• Experience with building AI features using LLMs and evaluation frameworks
• Exposure to MLOps best practices
• Knowledge of microbiome data, ---omics pipelines, or biomarker analytics

Benefits

• Competitive health insurance
• Parental policies
• Professional development programs
• Remote work
• Flexible work environment