AI Operations Engineer

020 Cisco Systems, Inc.; Bengaluru; On-site; INR 2,000,000 - 4,500,000; Full time

Job summary

Cisco Systems, Inc. is seeking an AI Operations Engineer to join the Commerce Operations Engineering Center.

You will help translate operational requirements into reliable, scalable AI solutions and collaborate with AI, engineering, and operations teams to integrate AI-driven automation across commerce workflows. The role focuses on developing AI agents, building RAG pipelines, implementing guardrails, and delivering observable, production-ready solutions through CI/CD and robust testing.

Qualifications

• 3+ years of experience in software/AI/data engineering or a related field.
• Experience developing LLM-powered, machine-learning, or automation applications.
• Proficiency in Python and experience with one or more LLM or agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, OpenAI SDK, or Anthropic SDK.
• Working knowledge of retrieval-augmented generation, prompt engineering, tool calling, and workflow orchestration.
• Experience developing API and system integrations using REST, GraphQL, event-driven services, authentication, or enterprise data sources.
• Familiarity with Git, testing, debugging, code reviews, and CI/CD.

Responsibilities

• Develop and enhance AI agents that automate manual and repetitive Commerce Operations tasks.
• Implement agent workflows using frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent.
• Support agent-to-agent integrations using standards such as A2A and MCP.
• Develop secure API integrations with commerce platforms and enterprise data sources using REST, GraphQL, webhooks, and event-driven services.
• Apply authentication, rate limiting, validation, and error-handling practices to system integrations.
• Build and maintain retrieval-augmented generation (RAG) pipelines using documents, structured data, and enterprise knowledge repositories.
• Implement defined guardrails, human approval steps, LLM routing, and failover mechanisms.
• Apply prompt and context engineering techniques to improve accuracy, safety, and consistency of AI outputs.
• Contribute to evaluation and observability capabilities, including test data sets, tracing, audit logging, monitoring, and quality regression detection.
• Support deployment and production operations through CI/CD, version control, monitoring, rollback processes, and cost tracking.
• Monitor AI solution performance and help report business outcomes using metrics such as efficiency gains, cycle-time reduction, incident reduction, and operational accuracy.
• Troubleshoot issues and continuously improve AI workflows, tools, and development practices.
• Collaborate with Commerce Operations, application development, infrastructure, and business teams to integrate AI solutions into existing systems and workflows.
• Document technical designs, integrations, test results, and operational procedures.

Skills

Python

LLM frameworks

API integrations

Git & CI/CD

Problem solving

Tools

LangChain

LangGraph

OpenAI SDK

Anthropic SDK

REST/GraphQL

Job description

Meet the Team Join Cisco’s Commerce Operations Engineering Center (COEC) as an AI Operations Engineer. You will be part of a collaborative team developing AI-powered automation solutions. Working with AI, engineering, and operations teams, you will help translate operational requirements into reliable and scalable AI solutions that support Cisco’s AI-first future.

What You’ll Do

• Develop and enhance AI agents that automate manual and repetitive Commerce Operations tasks.
• Implement agent workflows using frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent.
• Support agent-to-agent integrations using standards such as A2A and MCP.
• Develop secure API integrations with commerce platforms and enterprise data sources using REST, GraphQL, webhooks, and event-driven services.
• Apply authentication, rate limiting, validation, and error-handling practices to system integrations.
• Build and maintain retrieval-augmented generation (RAG) pipelines using documents, structured data, and enterprise knowledge repositories.
• Implement defined guardrails, human approval steps, LLM routing, and failover mechanisms.
• Apply prompt and context engineering techniques to improve the accuracy, safety, and consistency of AI-generated outcomes.
• Contribute to evaluation and observability capabilities, including test datasets, tracing, audit logging, monitoring, and quality regression detection.
• Support deployment and production operations through CI/CD, version control, monitoring, rollback processes, and cost tracking.
• Monitor AI solution performance and help report business outcomes using metrics such as efficiency gains, cycle-time reduction, incident reduction, and operational accuracy.
• Troubleshoot issues and continuously improve AI workflows, tools, and development practices.
• Collaborate with Commerce Operations, application development, infrastructure, and business teams to integrate AI solutions into existing systems and workflows.
• Document technical designs, integrations, test results, and operational procedures.

Minimum Qualifications

• 3+ years of experience in software engineering, AI engineering, data engineering, or a related field.
• Experience developing LLM-powered, machine-learning, or automation applications.
• Proficiency in Python and experience with one or more LLM or agent frameworks, such as LangChain, LangGraph, AutoGen, CrewAI, OpenAI SDK, Anthropic SDK, or equivalent.
• Working knowledge of retrieval-augmented generation, prompt engineering, tool or function calling, and workflow orchestration.
• Experience developing API and system integrations using REST, GraphQL, event-driven services, authentication, or enterprise data sources.
• Familiarity with software development practices, including Git, testing, debugging, code reviews, and CI/CD.
• Ability to solve technical problems and collaborate effectively with business and engineering teams.

Preferred Qualifications

• Familiarity with agent interoperability standards and protocols, including A2A, Model Context Protocol (MCP), and OpenAPI-based tool integration.
• Exposure to multi-agent systems, human-in-the-loop workflows, and AI agent guardrails.
• Experience with evaluation and observability tools such as LangSmith, Langfuse, tracing tools, evaluation harnesses, or equivalent AgentOps/LLMOps platforms.
• Knowledge of vector databases and retrieval methods, including semantic search, hybrid search, reranking, or knowledge-graph grounding.
• Familiarity with AI governance and safety practices, including role-based access control, audit logging, PII handling, and controls for automated actions.
• Experience with cloud platforms such as AWS, GCP, or Azure.