Software Engineer (Embedded Agentic AI)

About the team Roku TV organization builds technology used on millions of TVs globally, and the team is already applying AI to demanding TV problems in resource‑constrained environments where quality, performance, and reliability matter. As part of this team, you will help define how agentic AI systems are designed, built, and operated for Roku TV use cases. This is a hands‑on engineering role for someone who treats AI agent design as an engineering discipline: architecting durable systems, grounding them in the right context, integrating them with tools and services, and making them reliable in production. About the role We are looking for a hands‑on, systems‑oriented Agentic AI Engineer to design, build, and maintain intelligent agents and copilots that drive automation, accelerate workflows, and unlock new product and platform capabilities for Roku TV. You will own the full lifecycle of agent development—from prototyping and architecture through orchestration, evaluation, deployment, observability, and continuous improvement. You will contribute directly to Roku’s AI strategy by engineering reusable components, optimizing agent workflows, and ensuring strong real‑world performance in production environments. What you’ll be doing 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 and context design, retrieval strategies, backend services, and conversational interfaces. Design and implement single‑agent and multi‑agent orchestration patterns, including handoffs, delegation, and cooperative task execution. Build scalable RAG and context pipelines that provide high‑quality grounding for AI systems and keep them aligned with evolving data sources and business logic. Implement tool‑calling, function‑calling, and MCP‑style integrations so agents can safely take actions and interact with the systems around them. Create reusable agent templates, modular components, and paved‑path patterns that accelerate adoption across teams and use cases. Establish strong evaluation, observability, and monitoring for conversation quality, task success rate, latency, cost, and overall system performance. Build safeguards that improve production readiness and reliability, including testing pipelines, controlled rollouts, drift detection, and mechanisms that prevent error amplification in multi‑step workflows. Prototype quickly, run experiments, and translate successful ideas into durable, scalable software solutions. Partner closely with engineering, product, QA, infrastructure, and cross‑functional teams to deliver meaningful business and customer outcomes. We’re excited if you have Bachelor’s or master’s degree in Computer Science, Computer Engineering, Electrical Engineering, Data Science, or a related technical field. 2+ years of experience in software engineering, AI/ML engineering, backend development, or adjacent domains, with strong software engineering fundamentals and the ability to build production‑grade systems. Strong proficiency in Python, plus experience with C/C++ or another systems language. Hands‑on experience with LLM‑based systems, including prompt design, retrieval, tool use, memory handling, and agent orchestration patterns. Experience building and maintaining RAG pipelines, agent frameworks, MCP servers or equivalent function‑calling architectures, and conversational interfaces. Familiarity with cloud platforms, REST APIs, containerization, and modern deployment environments. Experience with observability, evaluation, experimentation, and feedback loops for AI systems in production. Ability to work independently, manage ambiguity, move quickly, and deliver incrementally in a fast‑paced environment. Excellent communication skills, sound engineering judgment, and a collaborative working style. Nice to have Experience with multi‑agent frameworks or orchestration systems such as LangChain, AutoGen, or Semantic Kernel. Experience with video, audio, TV, or edge‑device environments, especially where latency, cost, and hardware constraints matter. Familiarity with ML/DL frameworks such as PyTorch or TensorFlow. Research experience, paper implementation experience, or a habit of applying emerging GenAI techniques pragmatically to real problems. Our Hybrid Work Approach Roku fosters an inclusive and collaborative environment where teams work in the office Monday through Thursday. Fridays are flexible for remote work except for employees whose roles are required to be in the office five days a week or employees who are in offices with a five‑day in‑office policy. Benefits Roku is committed to offering a diverse range of benefits as part of our compensation package to support our employees and their families. Our comprehensive benefits include global access to mental health and financial wellness support and resources. Local benefits include statutory and voluntary benefits which may include healthcare (medical, dental, and vision), life, accident, disability, commuter, and retirement options (401(k)/pension). Employees are supported in taking time off, in accordance with local leave policies and other personal needs to support their evolving work and life needs. It’s important to note that not every benefit is available in all locations or for every role. For details specific to your location, please consult with your recruiter. Accommodations Roku welcomes applicants of all backgrounds and provides reasonable accommodations and adjustments in accordance with applicable law. If you require reasonable accommodation at any point in the hiring process, please direct your inquiries to View email address on click.appcast.io. #J-18808-Ljbffr