Rohan Murmu

Full Stack and Cloud Engineer with almost 2 years of experience building scalable backend systems, cloud services, microservices, and real-time applications. Experienced in integrating AI capabilities into backend systems and designing AI workflows around LLMs, RAG, agents, MCP, context engineering, and deploying AI services on cloud infrastructure, including VM and serverless environments.

Software Developer - Adrig AI Technologies - Chennai - Remote

(2024-11)

• Built and shipped LLM-powered backend systems for enterprise applications, integrating LangGraph, Ollama, and vLLM with existing Go, Node.js, and Python services to introduce AI capabilities without coupling application logic directly to model providers.
• Designed RAG-based knowledge retrieval systems using embeddings, Qdrant, Pinecone, and LangChain, implementing document chunking, metadata filtering, semantic retrieval, and context assembly to ground LLM responses in application-specific data.
• Built real-time and asynchronous AI workflows using Redis, RabbitMQ, AWS SQS, and WebSockets, decoupling long-running AI operations from request/response APIs and providing live execution status to frontend clients.
• Containerized and deployed backend and AI workloads using Docker, Nginx, AWS EC2, S3, Lambda, Azure VM, and Cloudflare Workers, designing service boundaries and deployment configurations for independently scalable application components.
• Built automated testing and CI/CD pipelines using GitHub Actions and Jenkins, integrating Jest, Supertest, and Playwright to validate backend APIs, AI-enabled workflows, and end-to-end application behavior before deployment.

Integrated B.Tech+M.Tech - Information Technology - Indian Institute of Information Technology (2019-07 - 2024-10)