SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
F5 Digital is building an enterprise-scale Agentic AI platform and seeks a Principal AI Software Development Engineer to serve as the technical authority and hands-on architect for high-code agent development, orchestration frameworks, and enterprise AI integration during the Gemini rollout.
This is a deeply technical individual contributor role focused on designing and implementing scalable agentic systems, establishing engineering standards for AI workflows, and enabling engineering teams to build production-ready agents using Gemini, Vertex AI, and internal AI infrastructure.
Key responsibilities include:
**Agentic Architecture & Orchestration**: Design and implement enterprise-grade agent orchestration frameworks supporting tool use, memory, RAG, agentic workflows, and automation. Establish patterns for multi-agent collaboration, event-driven execution, and workflow chaining across enterprise systems. Define standards for agent lifecycle management, state persistence, and context engineering.
**Gemini & Vertex AI Integration**: Lead technical integration of Gemini models via Vertex AI, ensuring secure, scalable API consumption and proper model routing. Develop internal SDKs, abstractions, and reusable components to standardize Gemini usage across F5 teams. Optimize prompt engineering, token efficiency, grounding strategies, and structured output patterns.
**High-Code Agent Enablement**: Build reference implementations and reusable frameworks for high-code agents in Java, Python, Go, or TypeScript. Establish secure integration patterns for agents interacting with Salesforce, Snowflake, SharePoint, ServiceNow, and internal APIs. Drive best practices for MCP (Model Context Protocol) server development and secure API mediation.
**Observability, Safety & Governance**: Implement logging, tracing, telemetry, and evaluation pipelines for agent performance and reliability. Establish guardrails including input/output validation, hallucination mitigation, prompt injection defenses, and policy enforcement. Partner with Security to ensure secure data handling, RBAC enforcement, and compliance alignment.
**Developer Enablement & Technical Leadership**: Support engineering teams adopting Gemini Code Assist, CLI workflows, and internal AI development platforms. Create technical documentation, internal libraries, and code samples for no-code, low-code, and pro-code agent builders. Provide architectural review and guidance for AI-enabled applications across F5.
**Performance & Scalability**: Optimize inference latency, parallelization, and cost management strategies across agent workflows. Implement caching strategies, streaming responses, and batching techniques to improve throughput and reliability. Evaluate and benchmark agent/model performance across different workloads.
Required: 10+ years software engineering experience with significant distributed systems and backend architecture expertise. Deep hands-on coding in Python and at least one of Go, Java, or TypeScript. Production experience with LLM-based systems including prompt engineering, tool calling, RAG, embeddings, and agent frameworks. Experience with Vertex AI, Gemini APIs, OpenAI APIs, or similar enterprise AI platforms. Strong understanding of API design, microservices, Kubernetes, and cloud-native architectures. Experience building or integrating orchestration frameworks (LangChain, LlamaIndex, custom layers). Familiarity with vector databases, embedding pipelines, and retrieval strategies. Strong understanding of authentication, authorization, and enterprise security patterns. Proven ability to build reusable platforms, not point solutions.
