Software Engineer, Agentic AI

Overview

In this role you will design, build, and operate intelligent AI agents and copilots for Roku TV, enabling automation and new product capabilities. You’ll own the full lifecycle from prototyping to production, ensuring reliable, scalable agent systems. You will contribute to Roku’s AI strategy by creating reusable components and optimizing agent workflows. Expect cross-functional collaboration to deliver meaningful business outcomes. This is a hands-on, impact-driven opportunity in a fast-paced, scale-focused environment.

Pay / Benefits

• global mental health and financial wellness resources
• healthcare (medical, dental, vision)
• retirement options (401(k)/pension)
• paid time off and leave policies
• accommodations and adjustments
• flexible remote Fridays (hybrid culture)

Responsibilities

• Architect, develop, and deploy AI agents and copilots for Roku TV use cases, integrating with internal systems and services
• Own end-to-end agentic systems from concept to production, including model selection and conversational interfaces
• Design single-agent and multi-agent orchestration patterns with handoffs and delegation
• Build scalable RAG and context pipelines for high-quality grounding
• Implement tool-calling and MCP-style integrations for safe system interactions
• Create reusable agent templates and modular components
• Establish evaluation, observability, and monitoring for quality, latency, and cost
• Develop production safeguards, testing pipelines, and drift detection
• Prototype quickly, run experiments, and translate ideas into durable software
• Partner with engineering, product, QA, infrastructure, and cross-functional teams

Key requirements

• Bachelor’s or master’s degree in a technical field
• 2+ years in software engineering, AI/ML engineering, backend development, or related domains
• Strong Python, with experience in C/C++ or other systems language
• Hands-on experience with LLM-based systems, including prompts, retrieval, memory, and orchestration
• Experience building and maintaining RAG pipelines, agent frameworks, MCP servers or equivalent, and conversational interfaces
• Familiarity with cloud platforms, REST APIs, containers, and modern deployment environments
• Experience with observability, evaluation, experimentation, and feedback loops for AI in production
• Ability to work independently, handle ambiguity, and deliver incrementally in a fast-paced environment
• Excellent communication and collaborative working style

• excellent communication
• collaborative
• adaptable
• Python
• C/C++
• LLM-based systems

…