Senior Data Scientist, Decision Science

We already run two kinds of agent alongside our teams. AI agents diagnose performance problems and tell people the root cause. Rule-based agents recommend marketing actions to our advertising teams. The quality of their decisions shows up directly in our revenue.

Next, both take a greater role in the day-to-day running of our lead generation business. Every agent needs predictions and decisions, so we need someone who brings both skill sets. Classical ML to predict lead quality and traffic performance, explain drops and forecast. Decision science to learn which action works best when, and prove it beats the rules.

You'll join a small data science team and work day to day with our AI engineers, product managers and the operators who use the agents.

Classical ML

• Build models. Classification and ranking for lead quality and traffic performance, anomaly detection, and forecasting.

• Evaluate and monitor them. Sound validation offline, drift checks once live, working with our platform team, who run model deployment on Sage Maker.

• Prove impact. Measure each model against commercial KPIs, with A/B tests where we can randomise.

Decision science

• Frame decisions. Turn a business rule into actions, context and reward, agreeing with operators what each decision optimises, with today's rules as the baseline.

• Learn policies. Contextual bandits with safe exploration, learning from operator overrides, evaluated off-policy before anything goes live.

• Set the evidence for hand-over. Measure how often agents agree with experts and how often they're overridden, and propose the confidence and guardrails an agent must clear before it acts alone. Point people in the business sign off; our AI engineers build the mechanism that enforces it.

• Summer Fridays

• Competitive holiday benefits - 25 days a year paid holiday, plus 8 bank holidays (increases 1 day a year up to 30 days)

• Hybrid working - 3 days a week in the office

• Closed for Christmas holidays - Extra days not taken from your annual holiday allowance.

• Work from anywhere for 2 weeks a year

• Life Assurance and Income Protection to protect your loved ones

• Benefits allowance for health, dental, and vision coverage

• Six months paid maternity leave, and one month paid paternity leave (subject to qualifying conditions) inclusive of same-sex and adoptive parents

• Defined Contribution Pension and Salary Sacrifice Scheme

• Be Well:
  Our award-winning wellbeing and mental health programme to support all MVFers and their families

• Family Forward support for our MVF parents and their mini-mes

• 2 charity days a year

• 5+ years as a data scientist or in a similar applied ML role, with models you've taken to production and kept working.

• Statistics and experimentation: hypothesis testing, A/B testing, power and sample sizing.

• Classical ML: classification and ranking with scikit-learn and XGBoost or LightGBM, evaluated rigorously: validation design, calibration, leakage.

• Decision science: applied work with at least one of contextual bandits, causal inference or uplift modelling, and the depth to apply it independently.

• Tools: strong Python and SQL, Git and code review.

• Production experience with bandits, off-policy evaluation or uplift modelling (for example Vowpal Wabbit, Open Bandit Pipeline, EconML or DoWhy).

• Time-series forecasting for budgets, pacing or demand.

• Snowflake and dbt, AWS Sage Maker.

• Lead generation or ad tech.

• Commercial impact. You understand how the business creates value and use that to make better choices about what gets built, prioritised or stopped. You define the intended impact before starting, consider the cost of the work and evaluate what happened afterwards.

• Delivery and ownership. You…