Senior Software Engineer

The application window is expected to close on: 11/19/2026 Meet the Team We're building an enterprise platform for AI agents — the shared foundation that lets engineering teams build, deploy, and run agents that are secure, reliable, and cost-effective at scale. Agents built on the platform serve customers, partners, and internal teams across many products and channels. As a Senior Software Engineer, you'll help build the platform end to end, collaborate closely with a team of engineers, and stay deep in the code. Your Impact As a Senior Software Engineer on the AI Platform, you will play a crucial role in advancing how the organization builds and operates AI agents — by contributing to the architecture, design, development, and operation of a modern, enterprise-scale agent platform. You'll work hands-on across every part of the platform: the agent harness and SDK that engineers use to build and run agents; the AI infrastructure and governance that provide secure, policy-controlled access to models, tools, and data; context and memory systems that get agents the right information at the right time; evaluation and observability that measure agent quality, cost, and behavior; the AI user experiences that bring agents into applications and partner integrations; and applied agents built in production alongside domain teams. • Contribute to the design and delivery of the platform, from first design through production operation. • Write code, review designs and pull requests, and take on hard technical problems. • Build reusable platform capabilities that other teams can depend on, with clear interfaces, versioning, and documentation. • Uphold engineering standards for quality, security, observability, and evaluation. • Improve latency, reliability, and cost for production AI workloads. • Run what you build: help define SLOs, take part in on-call, and participate in incident reviews. • Work with technologies like Python, LangGraph/LangChain, FastAPI, MCP, Kafka, PostgreSQL/pgvector, OpenTelemetry, Docker, and Kubernete • Partner with architects, product managers, security, and domain teams to translate business requirements into technical solutions. • Share knowledge and mentor peers through code reviews, design discussions, and documentation. Minimum Qualifications • Bachelor's degree +7 or a Masters +4 years of experience in building and running production backend or distributed systems. Degree is expected to be in computer science or a related field • Experience shipping LLM-powered applications or agents to production, and handling failure. • Experience with Python, and experience designing frameworks, SDKs, or platform APIs that other engineers build on. • Experience with distributed systems fundamentals: API design, asynchronous and event-driven processing, streaming, caching, rate limiting, and fault tolerance. Preferred Qualifications • Clear written communication: including design docs that explain trade-offs to both engineers and leadership • Agent development: tool/function calling, multi-step and multi-agent orchestration, durable execution, and human-in-the-loop approvals, using LangGraph/LangChain or comparable frameworks. • Agent interoperability: exposing agents and tools through open protocols such as MCP, A2A, and A2UI. • Context engineering: RAG, vector and hybrid search, and memory — with PostgreSQL/pgvector, OpenSearch/Elasticsearch/Qdrant, Redis, and embedding/reranking models. • Models and LLM infrastructure: major providers (OpenAI, Anthropic, Google Gemini, Bedrock, Azure OpenAI); vLLM; gateways such as LiteLLM; plus routing, token/cost management, caching, and latency optimization • Backend and APIs: FastAPI, asyncio, and Pydantic; REST, gRPC, SSE, and WebSockets; event streaming with Kafka. SQL and Java are a plus. • Evaluation and observability: eval datasets, rubrics, and LLM-as-judge; OpenTelemetry (incl. GenAI conventions), LangSmith, Ragas/DeepEval, Prometheus, and Grafana. • AI safety and governance: guardrails, prompt-injection defense, PII detection/redaction, and sandboxed execution (NeMo Guardrails, Llama Guard, Presidio, gVisor, or Firecracker). • Security: OAuth 2.0/OIDC/JWT; workload identity (e.g., SPIFFE/SPIRE); tenant isolation and audit logging; policy as code with Open Policy Agent or Cedar; secrets management such as Vault. • Cloud-native infrastructure: Docker, Kubernetes, and Helm; Terraform; a major cloud (AWS, Azure, or GCP); CI/CD such as GitHub Actions or Jenkins. • AI user experiences: React with streaming chat/agent interfaces and generative UI toolkits such as the Vercel AI SDK, A2UI, or MCP-UI. • Bonus: building an internal platform/SDK adopted by multiple teams; running AI systems for enterprise customers; open-source contributions to agent frameworks or protocols. Why Cisco? At Cisco, we’re revolutionizing how data and infrastructure connect and protect organizations in the AI era – and beyond. We’ve been innovating fearlessly for 40 years to create solutions that power how humans and technology work together across the physical and digital worlds. These solutions provide customers with unparalleled security, visibility, and insights across the entire digital footprint. Fueled by the depth and breadth of our technology, we experiment and create meaningful solutions. Add to that our worldwide network of doers and experts, and you’ll see that the opportunities to grow and build are limitless. We work as a team, collaborating with empathy to make really big things happen on a global scale. Because our solutions are everywhere, our impact is everywhere. We are Cisco, and our power starts with you. Message to applicants applying to work in the U.S. and/or Canada: The starting salary range posted for this position is $167,700.00 to $245,200.00 and reflects the projected salary range for new hires in this position in U.S. and/or Canada locations, not including incentive compensation*, equity, or benefits. I