LLM Operations Engineer

Overview

Design, deploy, and operate intelligent, autonomous solutions using Generative AI, Large Language Models (LLMs), Machine Learning Operations, and Agentic AI. Build LLM-powered, agent-driven architectures that reason, collaborate, and execute complex workflows across enterprise systems.

What you'll do

• Design and build multi-agent AI systems capable of planning, reasoning, and task execution.
• Develop applications using LLMs, including GPT, Claude, and Llama, with advanced prompt engineering and orchestration.
• Implement Agentic workflows using planner, executor, critic, and memory loops.
• Build Retrieval-Augmented Generation pipelines with vector databases for enterprise knowledge grounding.
• Develop tool-using agents that integrate with APIs, databases, and enterprise systems.
• Architect and deploy AI copilots and autonomous assistants for business workflows.
• Optimize LLM performance using fine-tuning, prompt chaining, and caching strategies.
• Implement short-term and long-term memory mechanisms using vector stores and knowledge graphs.
• Design multi-agent collaboration protocols, including hierarchical, swarm, and role-based agents.
• Deploy scalable solutions using MLOps and LLMOps practices, including monitoring, evaluation, and guardrails.
• Ensure AI safety, governance, and responsible AI practices.
• Utilize cloud-native services and tools for scalable and efficient deployment.
• Monitor LLM performance, address operational challenges, and ensure compliance and security standards in AI operations.
• Communicate with business stakeholders to translate workflows into agent pipelines.

What you'll need

• Generative AI.
• Large Language Models (LLMs).
• Machine Learning Operations.
• Agentic AI.
• Minimum 3 year(s) of experience.
• Minimum 3 years of experience in Generative AI.
• 3–8 years' experience in AI/ML with strong focus on Generative AI.
• Strong Python development skills.
• Experience building multi-agent orchestration systems with role-based coordination.
• Exposure to agent planning algorithms, including ReAct, Plan-and-Execute, and Tree of Thought.
• Experience with LLM evaluation frameworks, including RAGAS, TruLens, and Promptfoo.
• Knowledge of graph-based reasoning and knowledge graphs.
• Building autonomous systems or copilots in enterprise environments.
• Systems thinking for designing autonomous AI architectures.
• Strong problem decomposition for agent task design.
• Ability to balance latency, cost, and accuracy in LLM systems.
• Innovation mindset with focus on applying agentic AI in production.
• Hands-on experience with LLMs and GenAI frameworks.
• Hands-on experience with OpenAI and Hugging Face Transformers.
• Hands-on experience with agent frameworks: LangChain, AutoGen, CrewAI, and Semantic Kernel.
• Hands-on experience with RAG pipelines and vector databases: FAISS, Pinecone, and Weaviate.
• Experience building API-driven, tool-integrated AI agents.
• Strong understanding of prompt engineering and prompt optimization.
• Strong understanding of chain-of-thought reasoning and tool augmentation.
• Strong understanding of context management and token optimization.
• Experience with cloud platforms, with Azure OpenAI preferred and AWS/GCP acceptable.
• Knowledge of Docker, Kubernetes, and CI/CD pipelines.
• 15 years full time education.

Details

• Based at the Pune office.