Rajesh Maharana

I’m an AI Engineer with 5+ years of experience building enterprise-scale applications, cloud-native platforms, and Generative AI solutions across healthcare and enterprise environments. I specialize in designing and deploying production-grade Retrieval-Augmented Generation (RAG) systems, LLM-powered assistants, semantic search platforms, and intelligent document processing solutions.

In my current role, I’ve designed and developed Generative AI applications using OpenAI GPT-4 and Azure OpenAI to improve healthcare knowledge management and clinical workflow efficiency. I built production-grade RAG using LangChain, vector embeddings, and semantic retrieval techniques, and implemented intelligent document processing to extract, summarize, and classify content from PDFs, policy documents, healthcare records, and operational reports.

I also engineer end-to-end quality and safety: prompt orchestration with LangChain and LangGraph to improve answer quality and reduce hallucination, evaluation and monitoring frameworks for response quality and retrieval effectiveness, and secure architectures aligned with HIPAA requirements, authentication, audit logging, and role-based access controls. Previously, as a Software Engineer, I built scalable microservices with Java, Spring Boot, Python, and REST APIs, modernized monolith-to-cloud architectures on Azure, and automated CI/CD pipelines to improve release velocity and operational reliability.