SW Engineer Intern, AI Engineering

About The Role

Join Roku as an Engineering Intern and help build the agentic AI powering America’s #1 TV streaming platform. This is a paid 12-week internship, running from June to early September 2027. You’ll be assigned a scoped project with one of our engineering teams, working on real problems and learning how to take an AI-powered idea from prototype to production.

Key Responsibilities

• Own a well-defined project from problem definition through delivery.
• Build and test AI agents, copilots, and automated workflows that perform meaningful, multi-step work.
• Connect agents to trusted data, services, and internal tools using approaches such as retrieval, tool calling, and orchestration.
• Define agent autonomy and handover points to humans.
• Evaluate your work for effectiveness, reliability, and failure modes, and improve based on feedback.
• Utilize AI coding tools daily and validate their output through testing, review, and judgment.
• Write clean, well-tested, documented code.
• Participate in code reviews and collaborate with engineers, mentors, and cross-functional partners.

Requirements & Tech Stack

• Penultimate-year student, or a final-year student planning a one-year master’s course.
• Permanent right to work in the US.
• Available for full-time work for the entire 12-week program.
• Keen to work with AI technologies.
• Previous experience building AI agents and automated workflows.
• Currently enrolled in a degree program in Artificial Intelligence, Computer Science, Engineering, or a related field.
• Proficiency in Python, ideally with projects, open source, or hackathon work.
• Hands-on experience building an LLM-powered or agentic system that performs multi-step work.
• Familiarity with agentic patterns such as grounding, retrieval, tool use, orchestration, memory, or conversational interfaces.
• Sound engineering judgment, including validating AI-generated work and understanding failure modes.
• Solid grounding in computer science fundamentals such as data structures, algorithms, and operating systems or networking concepts.
• Strong problem-solving and technical communication abilities.
• Ability to break down ambiguous problems and deliver in small steps.
• Proactive mindset with passion for continuous learning and fast iteration.
• Experience with agentic engineering toolchain components like coding harnesses (e.g., Claude Code, Cursor), MCP servers, custom skills, or agent frameworks.

Qualifications

• You will be assigned a scoped project with one of our engineering teams and matched to the team that best fits your skills and interests.
• You’ll learn how to take an AI-powered idea from prototype to something people actually use, with a mentor and real ownership.
• Our teams work across a variety of languages and technologies, embracing AI-assisted development.