Waymo's Compute Team needs to deliver a high-performance compute platform for running the fully autonomous vehicle's software stack, requiring custom silicon, advanced system-level architectures, and close hardware/software collaboration to optimize performance, power, and latency for neural network inference.
Requirements
- Experience with compilers and parallel computing
- Strong C++ and/or Python programming skills
- Experience with domain-specific compilers, especially with neural networks
- 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
Responsibilities
- Architect, design, and implement compiler support for novel features of our unique neural network inference platform
- Analyze and enhance the behavior of existing compiler features to achieve optimal performance on state-of-the art neural networks
- Work together with model developers and hardware architects to improve the efficiency of inference hardware via software/hardware codesign
- Guide the development of future hardware solutions tailored to meet the needs of Waymo’s unique machine learning requirements
Other
- 3+ years of industry experience
- Waymo employees are also eligible to participate in Waymo’s discretionary annual bonus program, equity incentive plan, and generous Company benefits program, subject to eligibility requirements.
