Responsibilities Build, validate, and ship predictive models that drive the business: churn prediction, LTV forecasting, propensity and uplift modelling, and recommendation Own end-to-end ML workflows: feature engineering, model development, evaluation, deployment, and monitoring Monitor models in production and retrain or adjust them as the product and user base evolve Explore where AI/ML creates real product value as the company expands into AI-powered products Design and analyse experiments (A/B tests, uplift, causal inference), bringing rigour to how we measure impact and reduce variance Help shape the experimentation framework and modelling standards as foundations for the wider team Handle user-level data responsibly: privacy-aware feature engineering, avoiding leakage of sensitive attributes, and compliance with data-use policies Partner with Data Engineers to productionise models with reliable feature pipelines and, where useful, a feature store Translate model output into clear, actionable recommendations for Product, Growth, and leadership — tying work back to company goals Requirements 3+ years building and deploying machine learning models in a production setting Strong Python and SQL, with solid command of the modern ML stack (scikit-learn, plus PyTorch or TensorFlow where relevant) Sound grounding in statistics and experiment design: significance, causal inference, and uplift or propensity modelling Hands-on experience with predictive use cases: churn, LTV, propensity, or recommendation Comfort owning a model end to end — from problem framing to production and measurement, not just notebooks The ability to turn complex analysis into a clear narrative and a recommendation a non-technical stakeholder can act on Curiosity and autonomy — comfortable in a fast-moving environment where the roadmap evolves quickly #J-18808-Ljbffr
