LLM Application Engineer (Chennai)

Join Toptals Elite Network of Freelance Talent Toptal is an exclusive network of the worlds top freelance software developers, designers, finance experts, product managers, and project managers. As one of the fastest-growing fully remote networks globally, we empower professionals to thrive in their freelance careers while working with leading companies around the world. About the Client: Our client is an American research and advisory firm focusing on business and technology topics. The Role: We're looking for an AI Engineer to help build and scale a next-generation conversational AI initiative for a global research and advisory organization. This is a hands-on engineering role at the center of one of the most active areas in applied AI right now: production-grade conversational systems built on LLMs, retrieval-augmented generation, and autonomous agent architectures. You'll work on systems that go well beyond proof-of-conceptreal RAG pipelines serving real users, agent orchestration that has to behave reliably at scale, and infrastructure built on AWS and Azure's cloud AI stacks. If you like being close to the frontier of agentic AI and want your work to ship rather than sit in a notebook, this is built for that. Note: This role requires participation in a face-to-face interview with the hiring manager at a client location in Gurgaon or Chennai, India. Candidates based in or near these cities, or able to attend an in-person interview there, are strongly preferred. What You'll Do: Design, build, and deploy conversational AI systems and chatbots powered by large language models Develop and orchestrate AI agent architectures using frameworks such as LangChain, LangGraph, or LlamaIndex Build and maintain MCP (Model Context Protocol) server integrations to extend agent capabilities Architect and ship production-grade RAG (Retrieval-Augmented Generation) systems not prototypes, but systems serving live traffic Build and deploy LLM applications on AWS Bedrock an .