At Databricks, I build enterprise RAG solutions, scalable ETL pipelines, and real-time ML services. My work reduced document retrieval time by 60%, supported 50K+ daily inference requests at 99.5% availability, and improved prediction accuracy by 32%.
Previously at Capgemini, I analyzed multimillion-record datasets, built reporting and validation workflows, and delivered forecasting, segmentation, and predictive analytics solutions. I work across Python, PySpark, LLMs, MLflow, Databricks, AWS, and Azure to take AI products from data preparation through deployment and monitoring.
