Role Overview
We are seeking a hands‑on, systems‑oriented Agentic AI Engineer to design, build, and operate intelligent agents and copilots for Roku TV. The role focuses on architecting durable AI systems, integrating them with internal tools, and ensuring production reliability. You will own the full lifecycle from prototyping through deployment, evaluation, and continuous improvement, driving automation and workflow acceleration for Roku’s TV platform.
Responsibilities
- Architect and deploy AI agents and copilots for Roku TV use cases
- Own end‑to‑end agentic systems from concept to production, including model selection, prompt design, retrieval strategies, and backend services
- Design and implement single‑agent and multi‑agent orchestration patterns with handoffs and delegation
- Build scalable RAG and context pipelines for high‑quality grounding
- Implement tool‑calling, function‑calling, and MCP‑style integrations
- Create reusable agent templates and modular components
- Establish evaluation, observability, and monitoring for quality, latency, cost, and performance
- Build safeguards for reliability, including testing pipelines and drift detection
- Prototype quickly, run experiments, and translate ideas into scalable solutions
- Partner with engineering, product, QA, and infrastructure teams to deliver business outcomes
Requirements
- 2‑5 years of software engineering or AI/ML experience
- Bachelor’s or master’s degree in Computer Science, Electrical Engineering, Data Science, or a related technical field
- Proficiency in Python (or other major language) and experience with AI/ML frameworks
- Hands‑on experience building and deploying AI agents and copilots
- Familiarity with agentic AI toolchain (e.g., Claude Code, Cursor, MCP servers)
- Cloud platform experience, particularly AWS