LLM Operations Engineer

Overview

Design, deploy, and operate LLM-powered multi-agent systems and autonomous AI solutions for enterprise workflows. The role covers Agentic AI architecture, Generative AI applications, LLM operations, and responsible AI practices.

What you'll do

• Design multi-agent systems for planning, reasoning, and task execution.
• Develop LLM applications using prompt engineering and orchestration.
• Build RAG pipelines with vector databases for enterprise knowledge grounding.
• 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.
• Monitor, evaluate, and govern scalable AI solutions using MLOps and LLMOps practices.

What you'll need

• 3–8 years of experience in AI/ML with a strong Generative AI focus.
• Strong Python development skills.
• Experience with LLMs, Generative AI frameworks, and Agentic AI.
• Hands-on experience with OpenAI, Hugging Face Transformers, and agent frameworks.
• Experience building RAG pipelines, vector databases, and API-driven AI agents.
• Experience with cloud platforms and knowledge of Docker, Kubernetes, and CI/CD.
• 15 years of full-time education.

Details

• Based at the Pune office.