Staff ML Compiler Engineer, Compute

Waymo's Compute Team is tasked with a critical and exciting mission: We deliver the compute platform responsible for running the 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 with many other teammates to ensure the optimization of hardware and software for maximum performance.

In this hybrid role, you will report to an Engineering Manager.

You will:

• Analyze the performance characteristics of code generated by our production grade compiler and develop and implement engineering roadmaps for its improvement
• Architect, 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 through software/hardware codesign

You have:

• BS degree in Computer Science/Electrical Engineering or equivalent 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
• C++ programming skills

We prefer:

• 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

#LI-Hybrid