Description:

Owns predictive customer scores including churn, propensity, lifetime value, spend intent, and response scoring.
Applies machine learning and tabular predictive modeling to customer data, managing production models.
Works across the full model lifecycle: training, deployment, retraining, monitoring, evaluation, and calibration.
Supports predictive use cases with a focus on models running in production.

Requirements:

Experience with applied machine learning models in production environments.
Deep expertise in tabular predictive modeling on customer data.
Proven experience building churn or propensity models in telco, banking, or retail sectors.
Familiarity with training, deployment, and retraining pipelines in a self-managed environment.
Knowledge of MLOps practices including model registry, versioning, retraining, monitoring, and drift detection.
Comfortable working within a data platform rather than using notebooks.
Experience with uplift or causal modeling for incremental targeting.
Understanding of feature store design.
Ability to collaborate with commercial stakeholders on prediction applications.