Principal AI Engineer

F5•San Jose, CA

4d•Hybrid

About The Position

At F5, we strive to bring a better digital world to life. Our teams empower organizations across the globe to create, secure, and run applications that enhance how we experience our evolving digital world. We are passionate about cybersecurity, from protecting consumers from fraud to enabling companies to focus on innovation. Everything we do centers around people. That means we obsess over how to make the lives of our customers, and their customers, better. And it means we prioritize a diverse F5 community where each individual can thrive. Role Summary F5 Digital is building an enterprise-scale Agentic AI platform to enable secure, observable, and production-grade AI agents across the organization. We are seeking a Principal 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. The Principal Engineer will design and implement scalable agentic systems, establish engineering standards for AI workflows, and enable engineering teams to build production-ready agents using Gemini, Vertex AI, and internal AI infrastructure. The ideal candidate has strong distributed systems expertise, deep familiarity with LLM architectures and agent frameworks, and the ability to translate AI theory into secure, production-grade implementations.

Requirements

10+ years of experience in software engineering, with significant experience in distributed systems and backend architecture.
Deep hands-on coding expertise 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 (e.g., LangChain, LlamaIndex, custom orchestration 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.

Nice To Haves

Experience building multi-agent systems or autonomous workflow engines.
Experience with model evaluation pipelines and AI quality metrics.
Familiarity with structured output enforcement (JSON schemas, function calling).
Experience working with enterprise data systems such as Snowflake, Salesforce, ServiceNow, SharePoint.
Knowledge of cost modeling and inference optimization techniques.
Experience contributing to internal developer platforms or SDK ecosystems.
Background in AI safety, red-teaming, or model robustness evaluation.

Responsibilities

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.
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.
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.
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.
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.
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.

Benefits

You may also be offered incentive compensation, bonus, restricted stock units, and benefits.
More details about F5’s benefits can be found at the following link: https://www.f5.com/company/careers/benefits.
F5 reserves the right to change or terminate any benefit plan without notice.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume