Job Description As a Senior Data Scientist, you will be responsible for the following tasks: - Development of predictive and prescriptive models: Design and train Customer Segmentation models (clustering, RFM, behavioral profiling). Develop personalized recommendation engines (collaborative filters, content-based filters, hybrid systems) to improve cross-selling and upselling. Develop Prediction and Detection models: Churn, propensity, risk scoring, transaction volume forecasting, and detection of anomalies/behavioral rules for anti-money laundering (AML). - Data and model engineering: Collaborate with Data Engineers to define features and prepare the necessary training pipelines from the Data Lakehouse (Cassandra, Hive, etc.). Implement MLOps best practices: model versioning, deployment automation, and production performance monitoring (drift, bias). - Business value delivery: Translate business needs (e.g., reduce churn, increase conversion rate) into Data Science problems. Interpret model results and communicate insights to Product Owners and business stakeholders. Contribute to enriching source systems and the Data Lakehouse with predictive data.

Desired Candidate Profile

Education: Master's degree (Bac+5) in Engineering with a specialization in Data Science, Artificial Intelligence, or Applied Statistics/Mathematics. Experience: 3-5 years of proven experience on similar predictive modeling and recommendation systems projects. Technical Skills: Mastery of Machine Learning: Classic algorithms (regression, classification, clustering, time series) and Deep Learning (if applicable). AI Frameworks: Mastery of Python libraries (Scikit-learn, Pandas, XGBoost, TensorFlow, or PyTorch). Big Data & Tools: Knowledge of distributed environments (Spark/PySpark) and NoSQL databases (Cassandra, MongoDB). Ops & CI/CD: Familiarity with containerization environments (Docker) and model lifecycle management (MLOps). Technological ecosystem: Cloudera Data Platform, Microservices Architecture, Kafka, API Gateway (Axway), Keycloak. Methodology: Agile working methodologies (Scrum of Scrums, weekly progress meetings). Collaboration: Multidisciplinary team (Data Engineers, Lead Tech, Product Owners, Subject Matter Experts).