Senior Software Engineer - AI Automation

Teamwork makes the stream work. Roku is changing how the world watches TV Roku is the #1 TV streaming platform in the U.S., Canada, and Mexico, and we've set our sights on powering every television in the world. Roku pioneered streaming to the TV. Our mission is to be the TV streaming platform that connects the entire TV ecosystem. We connect consumers to the content they love, enable content publishers to build and monetize large audiences, and provide advertisers unique capabilities to engage consumers. From your first day at Roku, you'll make a valuable - and valued - contribution. We're a fast-growing public company where no one is a bystander. We offer you the opportunity to delight millions of TV streamers around the world while gaining meaningful experience across a variety of disciplines. About the role With more than 100 million people using our products globally, we’ve become well-known for products that “just work” right out of the box and integrate almost by magic. That doesn’t happen by accident, which is why we are committed to making sure our products aren’t just intuitive; they’re obvious. Our goal is to help people find what they want and make it easier for people to stream. We do this with state-of-the-art technology and engineering, keeping the customer at the center of everything we do. We're looking for a hands-on, systems-oriented Senior Software Engineer in Test (Sr. SDET) to join our Browse and Discovery Team. You'll own quality for the APIs and data pipelines — the automated test frameworks, containerized quality checks, CI/CD workflows, and infrastructure as code that let the rest of the organization ship with confidence. You'll do that work with agentic AI as your default mode of working: driving agents to write and maintain integration tests, keep suites healthy, triage failures, and debug production issues, and building the tools, harnesses, and evaluations that make those workflows trustworthy. This is a role for someone who treats agent design as an engineering discipline — grounding agents in the right context, integrating them with the systems they act on, proving them reliable through rigorous automation and evaluation, and turning what works into the reusable components and paved paths other teams at Roku build on. For California Only - The estimated annual base salary for this position is between $141,300 - $360,700. Compensation packages are based on factors unique to each candidate, including but not limited to skill set, certifications, and specific geographical location. This role is eligible for health insurance, equity awards, life insurance, disability benefits, parental leave, wellness benefits, and paid time off. How will I use AI at Roku? At Roku, we don't just use AI; we work with it. AI agents and smart tools help power drafts, analysis, and repetitive workflows, while our people bring direction, judgment, and accountability. We're looking for curious, adaptable builders who can show how they've used AI for automation to move faster, raise the bar, and scale their impact. We value your AI skills if you have built fluency across the agentic engineering toolchain — coding harnesses like Claude Code or Cursor, MCP servers, custom skills, or agent frameworks. And you can describe projects where you shipped real work with these tools. You know how to drive an agent, verify its output, and ramp on an unfamiliar codebase with an agent helping you. What you'll be doing Design and develop automated test frameworks for APIs and data pipelines, and containerize automated quality checks for complex orchestrated services. Use agentic AI workflows day to day — authoring and maintaining integration tests, keeping test suites healthy, triaging failures, and debugging production issues. Build the context and retrieval pipelines that ground these agents in the right code, schemas, telemetry, and business logic, and keep them aligned as those sources evolve. Implement tool-calling and MCP-style integrations so agents can safely act on the systems around them — test runners, CI, ticketing, logs, and data services. Build and maintain CI/CD workflows and infrastructure as code using Terraform or CloudFormation, so deployments and test execution are repeatable and auditable. Establish evaluation, observability, and monitoring for the signals that matter here: test reliability and flake rate, mean time to triage, agent task success rate, latency, and cost. Build safeguards that improve production readiness and reliability — controlled rollouts, drift detection, and mechanisms that prevent error amplification in multi-step agent workflows. Create reusable templates, modular components, and paved-path patterns that accelerate adoption across teams, and partner with development, data engineering, and product teams to improve end-to-end testing and release processes. We're excited if you have 5+ years of experience in software testing and automation, software engineering, or adjacent domains, with strong software engineering fundamentals and the ability to build production-grade systems. Expertise in Python or Java with familiarity in the other; experience with C/C++ or another systems language is a plus. Experience designing test plans, test cases, and automated test frameworks for APIs, services, and data pipelines. Hands-on experience with LLM-based systems, including prompt design, retrieval, tool use, memory handling, and agent orchestration patterns. Experience building and maintaining retrieval and context pipelines, agent frameworks, and MCP servers or equivalent function-calling architectures. Experience with CI/CD tooling such as GitLab runners, GitHub Actions, Jenkins, or Travis CI. Experience with cloud platforms — AWS (preferred), GCP, or Azure — REST APIs, and containerization and orchestration tools such as Docker and Kubernetes. Experience with infrastructure as code: Terraform or CloudFormat