Generative AI / Backend AI Intern

About this role

Design and build LLM and RAG-based systems from scratch while working on agentic architectures, vector pipelines, and backend AI services. Use technologies including Python, LangChain, LangGraph, OpenAI APIs, RAG workflows, Vector Databases, MCP, OCR, and prompt engineering tools in production-grade projects. The common technology stack includes FastAPI, MongoDB, Docker, Kubernetes, Git, Ubuntu, Bash, and CUDA for scalable AI deployment. Interns will gain hands-on experience deploying AI systems to production environments while working on live enterprise projects with startup-level ownership. The role offers exposure to scalable AI architectures, rapid growth opportunities, and ESOP benefits in a fast-moving AI startup. Applicants are expected to share their CV and GitHub profile while applying for the internship.