Jay Bergen

Designed, built, and optimized terabyte-scale data pipelines using Databricks, Apache Spark, and Azure Data Factory, ensuring seamless ingestion, transformation, and storage of structured and unstructured healthcare data. Developed and deployed LLM-powered document parsing systems leveraging OCR, deep learning models, and Graph Convolutional Networks (GCNs), improving data extraction accuracy by 4

Designed and implemented real-time fraud detection pipelines using Azure Synapse, Apache Spark, and Kafka, analyzing millions of transactions daily and reducing fraudulent activity by 30%. Developed high-performance ETL workflows in PySpark and SQL, increasing data processing efficiency by 50% for e-commerce datasets.

Developed financial ETL pipelines using Azure Data Factory, Python, and SQL, ensuring seamless aggregation of transactional data from multiple banking systems. Built and deployed fraud detection models using Isolation Forests and One-Class SVM, successfully reducing financial fraud risks.

Assisted in building Azure-based data ingestion pipelines, supporting large-scale ML projects. Developed ETL scripts for data normalization, improving query performance.

Completed a Master's degree in Information Science at the National University of Singapore, deepening expertise in advanced topics and research methodologies.

Studied Information Science at the National University of Singapore, focusing on foundational concepts and applications within the field.