Lead Data Scientist

The role

Machine-learning products

• Own the ML portfolio, including churn and segmentation, personalisation and recommendation engines, and demand forecasting for labour and operational planning.
• Frame business problems with stakeholders, choose an appropriate approach, and set success measures tied to commercial outcomes.
• Own model scoping, development, validation, deployment, monitoring, recalibration, and retirement.

ML Ops and production

• Set standards for version control, model registry, documentation, and governance.
• Work with Data Engineering to productionise models on GCP, Snowflake, and Airflow, with reliable scoring pipelines and usable outputs.
• Monitor production accuracy against thresholds and baselines, data drift, and business impact; provide alerts and review cycles.

Measurement and team development

• Set advanced measurement standards and advise analysts on experimentation, causal inference, and pragmatic alternatives where ideal methods are not possible.
• Create reusable frameworks, templates, and guidance for sound testing and impact measurement.
• Coach and upskill analysts and support data literacy across the business.

Stakeholders and delivery

• Partner with Membership, Marketing/CRM, Digital, Operations, and Finance to prioritise work by value.
• Explain complex methods and uncertainty to non-technical audiences, including senior leadership.
• Direct and quality-assure offshore data science work as needed by scoping tasks and reviewing code and models.

Essential experience and skills

• Typically 5+ years of hands-on data science experience across classification and propensity, recommendation, forecasting, clustering, and segmentation.
• Track record of deploying and owning production models, not just building prototypes.
• Strong Python and data science ecosystem skills; deep grounding in statistics, experimentation, and causal inference.
• Experience may include A/B testing, power analysis, variance reduction, difference-in-differences, synthetic control, or similar methods.
• Able to turn vague business questions into well-framed problems and explain results in plain English.
• Comfortable as a senior hands-on individual contributor who sets direction and reviews work without line-managing.

Desirable experience

• Modern cloud data stack experience, ideally Snowflake (Snowpark, Cortex) and dbt.
• Practical ML Ops experience, such as MLflow or similar, Git, CI/CD, containerisation, automated retraining, and monitoring.
• LLM and GenAI experience for development workflows or data enrichment.
• Experience in hospitality, membership, subscription, retail, or consumer businesses.
• Experience coaching analysts or building measurement and experimentation culture.

Benefits

• Benefits include global discounts, annual membership, enhanced pension, private health and dental care, Cycle to Work or Season Ticket Loan, and three paid charity-support days.
• The employer describes compensation as competitive and offers training for technical and managerial skills.