AI Operations Engineer

** 2021485 - AI Operations Engineer (Hybrid)*
* + This position is listed as hybrid - eligible candidates should expect to be present in the Raleigh-Cisco office on a semi-regular basis.

+ Job posting may be removed earlier if the position is filled or if a sufficient number of applications are received.

** Meet the Team*
* Join Cisco's Commerce Operations Engineering Center (COEC) as an AI Engineer, where you will be part of a dynamic team driving innovation through AI-powered automation. Collaborate with multi-functional AI, engineering, and operations teams to transform sophisticated operational challenges into reliable, scalable AI solutions that advance Cisco's AI-first future.

** Your Impact*
* As an AI Engineer in COEC, you will design, build, and operate production-ready AI agents that power Cisco's Commerce Operations. You will translate complex operational needs into automated workflows by orchestrating LLM reasoning, tool/function calling, retrieval, enterprise integrations, and agent-to-agent communication. You will be responsible for the full lifecycle of AI agent delivery-from solution design, guardrails, and system integration to evaluation, deployment, monitoring, and continuous improvement.

Your work will help eliminate manual tasks, improve speed and accuracy, and drive operational excellence.

** What You'll Do*
* + Design and build AI agents that automate manual and repetitive Commerce Operations tasks.

+ Implement agent orchestration using frameworks such as Lang Graph, Lang Chain, Auto Gen, CrewAI, or equivalent.

+ Build agent-to-agent integrations using emerging standards such as A2A and MCP to enable reliable coordination and delegation.

+ Design secure API integrations with commerce platforms and enterprise data sources using REST, GraphQL, webhooks, event-driven services, authentication, rate limiting, and error handling.

+ Build and optimize retrieval-augmented generation (RAG) pipelines using documents, structured data, and knowledge repositories.

+ Implement guardrails, human approval gates, LLM routing, and failover mechanisms to ensure reliability, safety, and cost control.

+ Apply prompt and context engineering to ensure AI agents deliver accurate, safe, and consistent outcomes.

+ Build evaluation and observability capabilities, including offline test sets, online monitoring, tracing, audit logging, and quality regression detection.

+ Own deployment and production operations, including CI/CD, progressive rollout, rollback, monitoring, model/version control, and cost tracking.

+ Supervise AI solution performance and report business impact through critical metrics such as efficiency gains, cycle-time reduction, incident reduction, and operational accuracy.

+ Continuously improve AI workflows, tools, and methodologies to increase reliability, scalability, and business value.

+ Partner with Commerce Operations, application development, infrastructure, and business teams to integrate AI solutions into existing systems and workflows.

** Minimum Qualifications*
* + 7+ years of experience in software engineering or a related field within an enterprise environment.

+ Shown experience building and deploying LLM-powered or agentic AI applications in production.

+ Strong Python skills and tactical experience with LLM/agent frameworks such as Lang Chain, Lang Graph, Auto Gen, CrewAI, OpenAI SDK, Anthropic SDK, or equivalents.

+ Practical expertise in retrieval-augmented generation (RAG), prompt engineering, tool/function calling, agent orchestration, and multi-agent communication or workflow orchestration.

+

Experience with API and system integrations, including REST, GraphQL, event-driven services, authentication, and enterprise data sources.

+ Demonstrated ability to lead technical delivery and collaborate effectively with multi-functional business and engineering teams.

** Preferred Qualifications*
* +

Experience with agent interoperability standards and protocols, including A2A, Model Context Protocol (MCP), and OpenAPI-based tool integration.

+ Skilled in designing enterprise-grade multi-agent systems, human-in-the-loop workflows, and implementing agent guardrails.

+ Validated experience with agent evaluation and observability tools such as eval harnesses, tracing, Lang Smith, Langfuse, or equivalent Agent Ops/LLMOps platforms.

+ Knowledge of vector databases and sophisticated retrieval methods, including hybrid search, reranking, multimodal retrieval, and knowledge-graph grounding.

+ Familiarity with AI governance and…