LLM Operations Engineer

Overview

Design, deploy, and operate scalable Generative AI and multi-agent systems, including LLM-powered applications, autonomous assistants, and enterprise workflows.

What you'll do

• Design multi-agent systems for planning, reasoning, and task execution.
• Develop LLM applications with prompt engineering and orchestration.
• Build RAG pipelines using vector databases.
• Integrate tool-using agents with APIs, databases, and enterprise systems.
• Deploy AI copilots and autonomous assistants for business workflows.
• Optimize LLM performance through fine-tuning, prompt chaining, and caching.
• Implement monitoring, evaluation, guardrails, safety, and governance.

What you'll need

• At least 5 years of experience is required.
• At least 3 years of experience in Generative AI.
• Strong Python development skills.
• Experience with LLMs, Generative AI frameworks, and agent frameworks such as LangChain, AutoGen, CrewAI, or Semantic Kernel.
• Experience with RAG pipelines and vector databases such as FAISS, Pinecone, or Weaviate.
• Experience with cloud platforms and Docker, Kubernetes, and CI/CD pipelines.
• 15 years of full-time education.

Details

• Location: Kolkata; the description also states that the position is based at the Pune office.