Senior Data Scientist - Banking Compliance

About the role

Devsinc is looking for an experienced Data Scientist focused on banking compliance to build, validate and deploy advanced analytics and machine learning solutions that support regulatory compliance, financial crime prevention and risk management. The role calls for combining strong data science expertise with deep knowledge of banking regulations, AML/KYC processes, sanctions screening and model risk management, delivering robust, explainable and audit-ready models.

Key responsibilities

• Design, develop, validate and monitor ML and statistical models for compliance, financial crime detection and risk management.
• Build predictive and anomaly detection models for AML, KYC, sanctions screening, transaction monitoring, customer risk scoring and fraud detection.
• Ensure models meet internal governance, regulatory and model risk management requirements, and carry out validation, performance testing, stability analysis, bias assessment and explainability reviews.
• Maintain model documentation, validation reports and audit-ready artifacts.
• Work with Compliance, Risk, Financial Crime, Technology and Data Engineering teams to turn business needs into analytical solutions.
• Analyze large structured and unstructured datasets to spot compliance risks, and set up model monitoring, dashboards and periodic reviews.
• Support internal audits, regulatory examinations and independent model validation, and mentor junior data scientists.

Required profile

• Bachelor's or Master's degree in Data Science, Statistics, Computer Science, Mathematics, Engineering, Finance or a related quantitative field.
• 6-8+ years of experience in Data Science, Machine Learning or Advanced Analytics in banking or financial services.
• Knowledge of banking regulatory requirements and compliance controls; understanding of AML, KYC, CDD/EDD, sanctions screening, transaction monitoring and financial crime risk management.

Required skills

• Strong Python and SQL.
• Machine learning libraries such as scikit-learn, XGBoost, PyTorch and/or TensorFlow.
• Experience building classification, anomaly detection, forecasting and risk-scoring models.
• Preferred: explainable AI (XAI), MLOps, model deployment and monitoring, and familiarity with AI/ML model governance expectations.