Senior Data Scientist - Financial Crimes Data Hub (EFCC/FIU) Role Purpose Partner with EFCC, FIU, FCBDP, and Solytics stakeholders to design and validate a scalable Databricks-based analytical data model that supports: Financial Crimes investigations AML transaction monitoring Entity resolution Behavioral analytics Alert generation and triage Network/link analysis Solytics anomaly detection capabilities Future AI/ML use cases The role will bridge business requirements, data architecture, and data science to establish a governed enterprise financial crimes data foundation. Required Technical Skills Databricks & Lakehouse Architecture Advanced Databricks experience Delta Lake design patterns Unity Catalog governance Medallion Architecture (Bronze / Silver / Gold) Data Product design Feature Store concepts Databricks SQL PySpark Spark optimization and performance tuning Data lineage and metadata management Desired Experience: Designing analytical data models in Databricks Large-scale cloud migration initiatives Financial services lakehouse environments Data Modeling Expertise Conceptual Modeling Ability to define:



Party Customer Household Account Transaction Alert Case Investigation Watchlist Relationship Counterparty entities and business relationships. Logical Modeling Experience designing: AML analytical models Fraud analytical models Network graph structures Feature-rich analytic marts Subject area models Physical Modeling Knowledge of: Delta tables Dimensional models Data Vault concepts Star and Snowflake schemas Slowly changing dimensions CDC processing Incremental loads Financial Crimes Analytics Strong understanding of: AML KYC CDD EDD SAR workflows Customer risk scoring Alert dispositioning Fraud Account fraud Payment fraud ACH fraud RTP fraud Behavioral anomalies Investigations Entity resolution Link analysis Network analysis Case management workflows Nice to have: Actimize experience Solytics experience Financial Services regulatory workplace Data Science & Machine Learning Skills Statistical Modeling Supervised learning Unsupervised learning Time-series analysis Clustering Anomaly detection Model Development Python PySpark Scikit-learn XGBoost MLflow Databricks Machine Learning Explainability Feature importance Model governance Regulatory transparency Fairness and bias evaluation

📌 Data Scientistv + DataBricks (Hyderabad)
🏢 GK HR Consulting India Private
📍 Hyderabad