Data Scientist

Must Have:

• Advanced Python for production data science and ML, including statistical matching, feature processing, model training and inference.
• Advanced SQL for campaign, customer, transaction, margin and measurement datasets.
• Strong hands-on Databricks experience: notebooks/modules, jobs/workflows, Delta/Unity Catalog data, model registry and production scoring.
• Git and Azure DevOps: branches, pull requests, code review, testing and controlled deployments.
• Production ML practices: reusable code, configuration, versioning, monitoring, logging, validation and operational handover.
• Databricks Apps, Streamlit, Dash or React for analytical decision-support interfaces; CRM Cost Calculator Tech Spec_UI identifies Databricks Apps, SQL Warehouse, Unity Catalog and Workflows as the preferred operational pattern.
• MLflow/model-registry and Databricks Asset Bundle experience.
• Familiarity with CRM activation platforms and campaign data, such as SFMC or Comarch.
• Marketing-mix, recommender-system or operations-research experience.

Data Scientist Role Overview:

Lead Data Scientist - Decision Science, Optimisation & Production ML Primary focus: BNA decisioning, causal/uplift modelling, offer economics, experimentation, constrained optimisation, model productionisation and monitoring.

Lead the design, development and production operation of CDI’s customer decision-science and optimisation capability, with particular accountability for BNA models, causal/uplift estimation, campaign recommendation, offer economics, experimentation and budget-constrained decisioning.