Sravan K. Email & Phone Number

United States

Chicago, Illinois, United States

Developed advanced Python applications for healthcare data processing, utilizing Gang of Four design patterns, asynchronous programming, and decorators to ensure optimal performance and maintainability for large datasets. Created robust agentic workflows in LangChain and Langraph to streamline complex healthcare processes, enabling intelligent AI agents to automate tasks such as patient data analysis and treatment recommendations. Leveraged Python and AWS in building secure and scalable data pipelines for healthcare analytics, enabling efficient processing of high-volume medical data for real-time insights. Established RAG workflows integrated with vector databases to retrieve relevant information for healthcare providers, improving response times and accuracy in patient care. Designed healthcare data APIs using Python, integrating patient information systems with MongoDB and DynamoDB to support secure and efficient data retrieval. Utilized AWS services such as Lambda and EC2 to deploy data-driven healthcare applications, ensuring scalability and reliability in high-demand settings. Employed Redis for fast and secure caching of patient data in Python applications, enhancing performance and reducing latency in healthcare analytics workflows. Created robust Python integrations between MongoDB and DynamoDB, allowing for seamless data flow between electronic health records and analytics tools. Worked with vector databases to optimize RAG-based healthcare solutions, ensuring precise data retrieval for accurate and timely medical insights.

New York, United States

Developed advanced Python applications for transaction monitoring and fraud detection in the banking domain, applying Gang of Four design patterns, asynchronous programming, and decorators to ensure efficient handling of high-frequency data. Designed agentic workflows using LangChain and Langraph to automate complex financial operations, enabling AI agents to support compliance checks and regulatory reporting. Implemented Retrieval-Augmented Generation (RAG) systems paired with vector databases to optimize retrieval of financial records, supporting real-time data access for customer service and fraud prevention. Deployed and managed banking applications on AWS, ensuring scalability and security to handle sensitive financial data in compliance with PCI-DSS standards. Built robust system integrations for banking databases and APIs, streamlining cross-system data sharing with automated transaction management, validation, and failure handling. Used LangChain and Langraph to create agentic workflows that facilitate real-time financial decision-making, enabling large LLMs to enhance customer support and advisory services. Developed RAG workflows leveraging vector databases for rapid retrieval of financial insights, ensuring accurate responses to client inquiries and enhancing risk assessment processes. Integrated banking data sources with AWS services such as Lambda and S3, optimizing data storage and retrieval for high-demand, real-time financial data analytics. Implemented Python-based solutions with Redis for caching transactional data, significantly improving response times and reducing load on core banking systems.

Austin, Texas, United States

Bengaluru, Karnataka, India

Hyderabad, Telangana, India