Sr. Software Engineer - Agentic AI

F5•Seattle, WA

2d•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. This role is grounded in F5’s BeF5 and LeadF5 principles: you put customers at the center, operate with ownership and accountability, build trust through inclusive collaboration, and raise the bar through technical excellence and continuous learning. You lead through influence—clarifying direction, aligning teams, and delivering outcomes with integrity. F5 is seeking an exceptional senior individual contributor to design and implement agentic experiences on F5’s Distributed Cloud Platform (F5XC). You will help create reliable, secure, and scalable agentic systems—spanning user experience, APIs, orchestration, evaluation, safety controls, and operational readiness. This role blends deep distributed-systems engineering with applied AI engineering to deliver production-grade agentic workflows customers can trust.

Requirements

Deep distributed systems expertise: Proven experience designing highly available, scalable services with strong operational rigor (resiliency patterns, rate limiting, backpressure, multi-region considerations).
Strong software engineering fundamentals: Expertise in one or more of Golang, Python, Java (or similar), with production-quality coding, testing, and API design practices.
Agentic systems experience: Hands-on experience building agentic applications/services (tool orchestration, function calling/tool APIs, RAG patterns, memory strategies, planning/execution loops, and failure recovery).
Security mindset: Understanding of common risks and mitigations in agentic/LLM systems (prompt injection, data exfiltration, tool misuse, authorization boundaries, tenant isolation).
Cloud-native proficiency: Experience with major cloud providers (AWS/Azure/GCP) and cloud-native architectures.
Containers and orchestration: Strong experience with Docker and Kubernetes (deployment patterns, image lifecycle, service networking, scaling strategies).
CI/CD and engineering hygiene: Git-based workflows, modern CI/CD, automated testing, and release discipline.
Data systems: Hands-on experience with SQL and/or NoSQL technologies and designing data access patterns for scale and correctness.
Communication and collaboration: Clear written/verbal communication; ability to align stakeholders, document decisions, and drive execution across teams.

Nice To Haves

Experience building multi-tenant SaaS platform services and/or edge/distributed compute offerings.
Experience with L3–L7 networking concepts relevant to secure application delivery (identity, routing, policy enforcement, gateways).
Experience building developer platforms/SDKs for AI or workflow orchestration.
Familiarity with observability stacks (metrics, logs, traces) and operating production systems at scale.

Responsibilities

Architect and build agentic experiences: Design and implement end-to-end agentic workflows (planning, tool-use, memory, retrieval, execution, and feedback loops) that are secure, observable, and reliable in production.
Platform-grade implementation: Deliver services/APIs that enable agentic capabilities on a multi-tenant SaaS platform, with strong guarantees around latency, scale, resiliency, and manageability.
Safety, security, and trust: Build guardrails for agentic behavior (policy enforcement, prompt/tool security, secrets handling, auditability, abuse prevention, and data boundaries) aligned with F5’s security mission.
Evaluation and quality: Define and automate evaluation strategies for agentic systems (offline test suites, regression harnesses, golden tasks, telemetry-driven iteration, and failure-mode analysis).
Operational excellence: Own reliability—instrumentation, tracing, debugging, runbooks, incident response learnings, and continuous improvement for agentic services in production.
Cross-functional leadership: Partner with Product, UX, Security, SRE, and Engineering teams across geographies to define requirements, shape roadmaps, and deliver customer value.
Mentorship and influence: Raise engineering standards through design reviews, code reviews, technical guidance, and by modeling inclusive collaboration and ownership.