Forward Deployed Engineer (FDE)

About the RoleWe are looking for a Forward Deployed Engineer (FDE) to design, build, and deploy production-grade AI systems in real customer environments.You will partner closely with our Product team, which owns the primary customer relationship, to translate customer needs, feedback, and business requirements into scalable technical solutions. Your work will span RAG pipelines, agentic workflows, LLM-powered applications, integrations, and cloud-native infrastructure, using real customer data and operating within real security, reliability, and compliance constraints.What You’ll DoOwn End-to-End Technical DeliveryPartner with Product to translate customer conversations, requirements, feedback, and commitments into clear, buildable technical plans.Own technical delivery from discovery and scoping through architecture, development, integration, testing, deployment, and production rollout.Build both proof-of-concepts and production solutions against real customer data, systems, APIs, infrastructure, and compliance requirements.Troubleshoot production issues and remain engaged through resolution.Build Production AI & Agentic SystemsDesign and build AI-enabled applications, RAG pipelines, agentic workflows, and automation systems.Work with agentic orchestration frameworks such as LangGraph, LangChain, CrewAI, DSPy, or ADK.Build solutions that integrate with and, where appropriate, extend our organization’s proprietary agentic AI framework rather than creating disconnected one-off implementations.Develop reusable agent-facing components including MCP servers, sub-agents, agent skills, tools, and agent-to-agent interfaces.Apply open standards such as the Model Context Protocol (MCP) alongside internal orchestration, governance, and engineering conventions.Design for Enterprise ScaleDesign architectures capable of operating under enterprise security, reliability, performance, and compliance requirements.Evaluate LLM hosting strategies across managed services such as Amazon Bedrock, Vertex AI, and Azure OpenAI, as well as self-hosted inference technologies such as vLLM, TGI, and Triton.Make informed architecture decisions around latency, cost, scalability, security, control, and token economics.Design policy-driven governance for agents, tools, and data access where appropriate.Evaluate AI system quality, safety, and performance using quantitative benchmarks and evaluation suites.Own the reliability and accuracy of the AI systems you deploy.Partner Across Product, Engineering & CustomersAct as Product’s technical counterpart throughout customer engagements.Translate ambiguous customer requests into technically feasible solutions and identify technical risks before external commitments are made.Join customer-facing sessions when deeper technical expertise is required.Present technical architectures, demos, findings, risks, and trade-offs to stakeholders ranging from engineers to executives.Collaborate closely with software engineering, security, platform, infrastructure, and Product teams.Identify reusable patterns from customer engagements and contribute them back to platform and engineering teams.Produce clear technical documentation, architecture diagrams, implementation guidance, and engineering best practices.Follow Cisco engineering, security, and Responsible AI practices, including policy-driven governance and compliance-as-code where applicable.What You’ll BringCore Engineering RequirementsProduction Software EngineeringYou have a demonstrated track record of shipping and operating production software, not simply developing prototypes that stop at proof-of-concept. You bring:Strong programming ability in Go and/or Python.Ability to write clean, maintainable, well-tested production code.Strong software engineering judgment and code review discipline.A quality-first mindset with experience across unit, integration, load, and AI evaluation testing, where appropriate.Comfort working collaboratively in small engineering pods through pairing, rapid reviews, and direct technical discussion.AI & Agentic SystemsYou have hands-on experience building AI systems beyond tutorials and experimental projects, including:At least one agentic orchestration framework such as LangGraph, LangChain, CrewAI, DSPy, or ADK.Production experience with RAG and semantic search architectures.Working knowledge of Model Context Protocol (MCP) and agent interoperability concepts.Experience building or integrating tool servers, agent skills, sub-agents, and agent-to-agent interfaces.Ability to quickly learn proprietary orchestration, skill-loading, and governance frameworks.Practical understanding of AI evaluation, observability, and safety.Experience monitoring model and agent behavior in production.Understanding of risks such as prompt injection, excessive permissions, unsafe tool calls, and tool-call scoping.Cloud & InfrastructureYou are comfortable working across modern cloud-native environments, including:Docker and Kubernetes.At least one major cloud platform: AWS, Azure, or GCP.CI/CD and deployment tooling such as GitHub Actions, Jenkins, CircleCI, ArgoCD, or GitOps-based workflows.Ability to create, troubleshoot, or extend deployment pipelines rather than relying entirely on infrastructure built by others.You should also understand the trade-offs between:Managed LLM APIs and self-hosted inference.Cost and performance.Latency and scalability.Operational control and managed services.Full-Stack CapabilityYou should be comfortable owning systems across multiple layers, including:Backend servicesAPIs and integrationsData pipelinesAI/LLM servicesCloud infrastructureDeployment pipelinesCustomer-facing API or UI layersYou do not need to specialize equally in every layer, but you should have enough range to understand and troubleshoot the complete system.Nice to HaveAdditional experience in any of the following areas is valuable:Policy-driven governance frameworks such as OPA or ABAC for agent tool access and data handling.MLOps/LLMOps, including model versioning, deployment, rollback, monitoring, and drift detection.Consulting, professional services, solutions engineering, or customer-embedded engineering.Streaming platforms such as Kafka.SQL and NoSQL databases.Enterprise security and compliance environments.