Waymo's Compute Team is tasked with a critical and exciting mission: We deliver the compute platform responsible for running the fully autonomous vehicle's software stack. To achieve our mission, we architect and create high-performance custom silicon; we develop system-level compute architectures that push the boundaries of performance, power, and latency; and we collaborate closely with many other teammates to ensure we design and optimize hardware and software for maximum performance. We are a multidisciplinary team seeking curious and talented teammates to work on one of the world's highest performance automotive compute platforms.

In this role, you'll:

• Analyze the performance characteristics of code generated by our production grade compiler and develop and implement engineering roadmaps for its improvement
• Architect, design, and implement compiler support for novel features of our unique neural network inference platform
• Guide model developers and hardware architects towards improving the efficiency and achieved performance of inference hardware via software/hardware codesign

At a minimum we'd like you to have:

• Relevant education/work experience
• BS degree in Computer Science/Electrical Engineering or equivalent practical experience and 7+ years of industry experience OR
• MS degree in Computer Science/Electrical Engineering and 5+ years of industry experience OR
• PhD degree in Computer Science/Electrical Engineering and 3+ years of industry experience
• 3+ years of industry and/or academic experience working on compilers for neural networks or linear algebra computation targeting parallel architectures
• 1+ years of experience in techniques used to generate code optimized for performance on a parallel architecture
• Strong C++ programming skills

It's preferred if you have:

• Python programming experience
• Knowledge of computer architectures used for neural network inference, and neural network performance characteristics
• Knowledge of the principles behind popular machine learning and neural network algorithms and applications

US-Remote includes employees working from their primary residence in certain locations only, such as Arizona, California, Colorado, Connecticut, DC, Florida, Georgia, Hawaii, Idaho, Illinois, Indiana, Maine, Maryland, Massachusetts, Michigan, Minnesota, Missouri, New Hampshire, Nebraska, New Jersey, New York, North Carolina, Ohio, Oregon, Pennsylvania, South Carolina, Texas, Utah, Virginia, Washington, and Wisconsin. This list may not be complete or accurate, and candidates should speak with their recruiter about their specific location for remote work.