Software Engineer, Agentic AI

As an Agentic AI Engineer for Roku TV, you design, build, and maintain intelligent agents and copilots that automate workflows and unlock new capabilities at scale. You own the full lifecycle from prototyping to production, focusing on reliable, production-ready systems. You will contribute to Roku’s AI strategy by developing reusable components and optimizing agent performance in a demanding, resource-constrained TV environment. You’ll collaborate with cross-functional teams to deliver meaningful customer outcomes, shaping how AI powers TV experiences.

• mental health and financial wellness support
• healthcare options (medical, dental, vision)
• life, disability, and accidental coverage
• retirement options
• commuter benefits
• flexible leave policies

• Architect, develop, and deploy AI agents and copilots for Roku TV use cases, integrating them with internal systems, tools, and services
• Own end-to-end agentic systems from concept to production, including model selection, prompt design, retrieval strategies, backend services, and conversational interfaces
• Design and implement single-agent and multi-agent orchestration patterns, including handoffs and cooperative task execution
• Build scalable RAG and context pipelines for high-quality grounding and alignment with data sources and business logic
• Implement tool-calling, function-calling, and MCP-style integrations for safe system interactions
• Create reusable agent templates and modular components to accelerate adoption across teams
• Establish strong evaluation, observability, and monitoring for quality, performance, latency, and cost
• Build safeguards and testing pipelines to improve production readiness and prevent error amplification in multi-step workflows
• Prototype quickly, run experiments, and translate ideas into durable software solutions
• Partner with engineering, product, QA, infrastructure, and cross-functional teams to deliver outcomes

• Bachelor’s or Master’s degree in a technical field
• 2-5 years of software/AI engineering with production-grade systems experience
• Strong Python proficiency; experience with C/C++ or another systems language
• Hands-on experience with LLM-based systems, including prompt design and orchestration
• Experience building/maintaining RAG pipelines, agent frameworks, MCP servers or function-calling architectures, and conversational interfaces
• Familiarity with cloud platforms, REST APIs, containers, and modern deployments
• Experience with observability, evaluation, experimentation, and feedback loops for AI in production
• Ability to work independently, manage ambiguity, and deliver incrementally in a fast-paced environment
• Excellent communication and collaborative skills

• curiosity
• adaptability
• strong communication
• Python
• C/C++
• LLM-based systems