Architected Generative AI solutions using Python, LangChain, Azure OpenAI, and vector databases to automate clinical document summarization, reducing manual review effort by 65% and enabling faster decision-making for healthcare operations teams across multiple provider networks. Engineered Retrieval-Augmented Generation (RAG) pipelines on Azure AI Search and Snowflake to deliver context-aware responses from millions of patient and operational records, improving answer relevance by 40%. Developed healthcare copilots using FastAPI, OpenAI APIs, and semantic search frameworks to streamline prior authorization and claims support workflows, reducing average case handling time by 35%. Orchestrated MLOps workflows using Azure ML, MLflow, Docker, Kubernetes, and GitHub Actions to automate model deployment, monitoring, and retraining, improving release frequency while ensuring governance and compliance.

Data Engineer at Medsix, USA

February 1, 2024 - January 1, 2026

Designed scalable healthcare data platforms using Azure Data Factory, Databricks, PySpark, and Snowflake to consolidate EHR, claims, and provider datasets into a unified analytics ecosystem supporting more than 25 enterprise reporting solutions. Constructed real-time ingestion pipelines using Kafka, Spark Structured Streaming, and Delta Lake, processing 8M+ healthcare transactions daily to improve data availability and reduce reporting latency. Implemented advanced data quality frameworks with Great Expectations and Python validation libraries, improving data reliability across critical healthcare datasets and reducing downstream issues by 45%. Optimized large-scale ETL workloads through partitioning, caching, and performance tuning to reduce pipeline execution time by 50% and improve resource utilization. Proactively collaborated with data scientists to provision feature-ready datasets within Snowflake and Databricks, accelerating predictive healthcare initiatives.

Data Engineer at The Cigna Group, USA

May 1, 2023 - February 1, 2024

Developed cloud-native data pipelines using Azure Data Factory, Python, SQL, and Azure Data Lake to integrate claims, member, and provider datasets into centralized analytics platforms supporting healthcare operations and regulatory reporting. Automated ingestion and transformation for large-scale healthcare data (3 TB/day) using PySpark and Databricks, improving data delivery consistency for actuarial and BI teams. Established metadata-driven ETL frameworks and monitoring solutions with Azure Monitor and Log Analytics to enhance pipeline observability and reduce production incidents by 30%. Refined data warehouse performance through query optimization, indexing strategies, and dimensional modeling to improve report response times and enable faster access to actionable healthcare insights. Partnered with compliance, analytics, and business stakeholders to deliver trusted datasets aligned with HIPAA requirements.

Data Analyst at Tata Capital, India

September 1, 2019 - August 1, 2022

Analyzed lending, customer, and financial datasets using Python, SQL, Informatica, and Hadoop technologies to support enterprise reporting, BI, and risk management initiatives across multiple business functions. Developed batch and incremental data processing workflows using Spark and Hive to prepare, transform, and analyze high-volume financial transaction data, improving reporting accuracy for loan servicing and credit operations. Automated data reconciliation, validation, and quality assurance across multiple financial systems, strengthening data integrity controls and reducing manual verification efforts by 40%. Performed data analysis, schema optimization, and SQL performance tuning to improve reporting efficiency and accelerate monthly reporting cycles. Collaborated with business analysts, risk teams, and stakeholders to create analytical data marts, KPI dashboards, and actionable insights.