Software Engineer, Agentic AI

About the role

This role focuses on designing and maintaining intelligent agents and copilots to automate workflows and enhance the Roku TV platform. You will manage the full development lifecycle of these systems, from initial architecture and prototyping to production deployment and monitoring.

Key facts

What you'll do

• Architect and deploy AI agents integrated with internal tools and services.
• Manage end-to-end agentic systems including model selection, context design, and retrieval strategies.
• Build multi-agent orchestration patterns for task execution and delegation.
• Develop RAG and context pipelines to ensure system alignment with business logic.
• Implement function-calling and MCP-style integrations for system interaction.
• Create modular agent templates to support cross-team adoption.
• Establish observability and evaluation frameworks for latency, cost, and task success.
• Build safety mechanisms such as drift detection and testing pipelines for production reliability.
• Collaborate with product, infrastructure, and QA teams to deliver customer outcomes.

Requirements

• 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, or backend development.
• Proficiency in Python and experience with C/C++ or another systems language.
• Experience with LLM-based systems including prompt design, memory handling, and agent orchestration.
• Familiarity with RAG pipelines, agent frameworks, and conversational interfaces.
• Knowledge of cloud platforms, containerization, REST APIs, and deployment environments.
• Experience with AI system observability and experimentation.

Nice to have

• Experience with multi-agent frameworks like LangChain, AutoGen, or Semantic Kernel.
• Background in video, audio, TV, or edge-device environments with hardware constraints.
• Familiarity with ML/DL frameworks such as PyTorch or TensorFlow.
• Research experience or a history of applying GenAI techniques to practical problems.

Skills & tools

• Python, C/C++, LLM orchestration, RAG, MCP servers, REST APIs, cloud platforms, containerization, LangChain, AutoGen, Semantic Kernel, PyTorch, TensorFlow.

Practical notes

• Hybrid work policy: generally in-office Monday through Thursday with flexible Fridays.
• Benefits include global mental health and financial wellness support, plus local healthcare, retirement, and leave options.
• Reasonable accommodations available upon request via EmployeeRelations@Roku.com.
• Applicants acknowledge the Roku Applicant Privacy Notice upon submission.