Description

In this role, you will architect, design, and lead the development of a state-of-the-art Inference platform for advertising, handling low latencies, high scale, and throughput. You'll mentor engineers, innovate at scale, and shape the future of machine learning at Roku, the #1 TV streaming platform.

Requirements

• M.S. or above in CS, ECE, or related field
• 10+ years developing and deploying large-scale distributed systems, 5+ in leadership
• Strong programming skills in high-performance languages
• Deep understanding of inference frameworks and ML system deployment
• Experience optimizing large-scale ML systems with GPU acceleration and HPC techniques

Responsibilities

• Lead design and development of a state-of-the-art Inference platform
• Oversee monitoring, observability, and tooling for system and model performance
• Identify and resolve system inefficiencies and performance bottlenecks
• Stay at forefront of inference frameworks, ML hardware acceleration, and distributed systems