Lead Machine Learning Inference Engineer (Advertising)

Join Roku's Advertising Performance group as a Lead Machine Learning Inference Engineer. In this role, you will architect and lead the development of a state-of-the-art inference platform for advertising. You will oversee the development of monitoring and observability tools, identify and resolve system inefficiencies, and stay updated on advancements in inference frameworks and distributed systems. This position offers a range of benefits, including medical, wellness, and financial benefits, unlimited paid time off, and work-from-home opportunities.

• Architect, design, and lead the development of a state-of-the-art Inference platform for advertising.
• Oversee the development of monitoring, observability, and other tooling to ensure system and model performance.
• Identify and resolve system inefficiencies, performance bottlenecks, and reliability issues, ensuring optimized end-to-end performance.
• We’re looking for a strong technical leader with deep experience in ML serving, high-performance computing, and industry standard frameworks - someone excited to mentor engineers, innovate at scale, and shape the future of machine learning at Roku
• Proven experience optimizing performance for large-scale machine learning systems, including a deep knowledge of SOTA model optimizations, hardware-software co-design, GPU acceleration, and HPC techniques
• Excellent communication and collaboration skills
• Contributions to open-source ML or systems projects
• Deep understanding of inference frameworks and ML system deployment
• Strong programming skills in high-performance languages
• Experience collaborating with and leading global, cross-functional teams
• M.S. or above in CS, ECE, or a related field
• Experience leading teams working on high-throughput, low-latency ML serving systems
• 10+ years of experience in developing and deploying large-scale, distributed systems, with at least 5 years in a leadership or technical lead role