At Elevance Health, I engineered a healthcare RAG pipeline with Python, LangChain, and vector search, integrating HL7 and FHIR datasets to improve clinical query accuracy by 32%. I also fine-tuned transformer models on de-identified claims data for patient risk stratification.
Previously, I developed data pipelines at Informative Web Solutions using PySpark, SQL, and Apache Airflow. My work included Snowflake data models and PostgreSQL and MongoDB query optimization; I also built a RAG-based clinical assistant and claims fraud detection models in academic projects.

