• Spearheaded the implementation of a real-time claims fraud detection and adjudication platform, capable of processing millions of claims per day. The system delivers a projected Million dollar annual savings with sub-millisecond SLAs per claim.• Led cross-functional teams of engineers to design a robust rule-processing engine UI, enabling seamless ingestion of historical data, integration with CMS public datasets, and deployment of production-ready rules, enhancing claims accuracy and scalability.• Architected cloud-native microservices to securely process large-scale medical images and sensitive documents. Achieved encryption with near-instantaneous performance (latency under 4 milliseconds) using Kubernetes and IBM hosted S3• Developed scalable pipelines to ingest data from sources such as HBase, Snowflake, and AWS S3, ensuring high-performance data retrieval and processing.• Designed and deployed advanced NLP-driven components, leveraging OCR to parse medical documents and highlight key insights, reducing manual review time for healthcare professionals.• Directed the deployment of pre-trained Large Language Models (GPT-4) to automate intelligent decision-making for pre-authorization requests, accelerating the approval/denial process.• Created real-time reporting dashboards to monitor claims processing systems, empowering the operations team with actionable insights and streamlined workflows.• Collaborated with business, operations, and Responsible AI teams to ensure applications adhere to industry standards and ethical guidelines.Championed the integration of external vendor solutions into the platform, enhancing capabilities for advanced claims processing and operational efficiency.

Worked as a developer in Data ingestion and fusion team. Ingestion is a complex software application that involves implementing various business rules to enhance the quality of data.This application leverages AWS resource , Big data technologies like Hadoop ,Spark ,Apache Airflow(Python) to meet demands of the business.Data Pipeline and Workflow ManagementDeveloped Airflow directed Acyclic Graphs(DAG) using Python based modules to implement data pipelinesInfrastructure Layer: AWS EMR , ECS containersCloud Based Application Development Developed Pyspark based modules for data processing and data validation using Amazon s3 for storage of data in cloud Performance Improvement of Existing application Tweaked Elastic Map Reduce configurations and spark parameters to bring down production runtime by 20 min . API development using AWS Lambda Function and API Gateway Worked on deploying AWS lambda function using Python that gets triggered by a REST api call from api gateway. This component validates incoming api calls based on some conditions. The Python script is tested using unit-test module before implementing on AWS platform. Implemented security best practices for api gateway using IAM keys Production System EnhancementsInvolved in supporting daily production jobs and code enhancements like sending automated emails with attachments to other teams.Used AWS cloud watch logs to monitor performance and debug errors.Data Quality Check and Regression Testing Responsible for rewriting code and upgrades to latest version .Prepared Golden dataset and scala scripts to test Scala modules to test data quality check and code efficiency.

Worked as a Class Room Assistant in Economics Department . Proficient in micro and Macro Economics