Data Engineer

Built real-time fraud detection data pipelines using Apache Kafka and PySpark Structured Streaming; modeled customer behavioral features in Snowflake using dbt; contributed to migrating legacy batch scoring workflows to event-driven services; automated CCAR stress-testing report generation; built a RAG-based compliance search tool; used MLflow and Evidently AI for model tracking and drift monitoring.

Developed and optimized PySpark AML transaction monitoring pipelines on Azure HDInsight; built feature engineering pipelines for fraud analytics; developed FastAPI microservices deployed on OpenShift and AKS; engineered Airflow DAGs for ingestion, validation, scoring, and SAR report generation; implemented data quality validation and reconciliation jobs; created Tableau dashboards.

Rebuilt the credit risk data mart in Snowflake using dbt and Airflow; wrote PySpark jobs on Azure HDInsight for AML transaction monitoring; containerized a retail credit scorecard pipeline and deployed it on AKS; exposed model predictions through FastAPI services; contributed to A/B testing and model governance documentation.

Built Python ETL pipelines to migrate transaction data from Oracle to PostgreSQL; developed NLP classifiers to route customer support tickets; automated financial reporting workflows; contributed to a KYC document verification module using OpenCV and Tesseract OCR; improved test coverage for Python data processing libraries.