
Senior Engineer with over 15 years of experience in developing scalable, observable, and resilient distributed systems across cloud, microservices, and enterprise platforms. Deep expertise in performance engineering, API scalability, system observability, and production reliability. Recently designed and implemented Retrieval-Augmented Generation (RAG) services utilizing Python FastAPI, FAISS vector search, OpenAI embeddings, and Docker, seamlessly integrated with Java/Spring APIs. Currently applying performance engineering principles to LLMOps, focusing on prompt regression testing, token monitoring, latency optimization, and AI service observability to enhance overall system efficiency.
Text to Claim – Dec 2024, Built a Docker-based system with Spring Boot and Python AI services enabling customers to file claims via SMS., Python AI service used BERT-based models to convert conversational text into structured data and map issues to problem codes., Automated claim creation and resolution suggestions via text interaction.,
SquareTrade GenAI(Ashronis) – Dec 2023, Built a GenAI Slack application using Python, Slack SDK, ChromaDB, and OpenAI., Generated embeddings from Confluence and JIRA data and stored in ChromaDB., Implemented similarity search retrieval and LLM response using contextual data.
AI Monitoring Assistant – Dec 2025, Developed an Agentic AI Monitoring Assistant that automates API performance monitoring across environments. It uses a Slack chatbot integrated with Dynatrace APIs to fetch, analyze, and present real-time performance, error, and infrastructure metrics instantly.