Data Science & Advanced Analytics Lead

Overview In this role you will design, build, and deploy scalable ML and analytics solutions across high-impact banking domains. You’ll work with cross-functional teams to operationalize AI in critical workflows, aiming to reduce losses, accelerate payments, and boost customer engagement and revenue. You’ll own end-to-end model delivery and governance in a production environment. This is a hands-on, impact-driven position at a bank focused on responsible AI and scalable analytics. ResponsibilitiesDevelop and deploy ML models for fraud detection, payments intelligence, cross-border scoring, NBA personalization, customer segmentation, churn prediction, and growth analyticsOwn end-to-end model delivery (framing problems, data engineering, feature engineering, development, validation, deployment, monitoring, improvement)Build scalable ML pipelines using Azure ML, Databricks, Spark, and cloud-native platformsOperationalize models via APIs, microservices, and real-time decision systemsDesign NBA strategies to optimize engagement, adoption, and lifetime valueDevelop fraud and payments models to reduce loss and improve authorizationImplement robust model governance, explainability, monitoring, recalibration, and compliance controlsEstablish MLOps best practices, CI/CD, experiment tracking, and production monitoringCollaborate with risk, compliance, legal, audit, and tech teams to ensure responsible AITranslate analytical findings into clear insights for senior leaders Key requirements10+ years in data science, ML, quantitative modeling, or advanced analytics in financial services or regulated industriesProven production-grade ML model delivery with measurable business impactDeep expertise in Python, SQL, statistical modeling, predictive analytics, and distributed data processingExperience with Azure ML, Databricks, Spark, TensorFlow, PyTorch, scikit-learn, XGBoost, MLflow, and cloud-native ML ecosystemsExperience implementing MLOps frameworks (CI/CD, deployment, monitoring, governance)Strong understanding of model risk management, explainability, auditability, data governance, privacy, regulatory expectationsHands-on experience integrating ML into enterprise apps, APIs, and operational workflowsStrong process orientation to redesign workflows using data-driven insights and AI-enabled automationAbility to influence senior stakeholders across business, risk, technology, and operationsExcellent communication and executive presentation skillsexcellent communicationstakeholder influencecross-functional collaborationPythonSQLstatistical modeling