Tesla - Austin, TX
posted 5 months ago
As a member of the Autopilot hardware team, you will be responsible for enabling Tesla's neural networks on our upcoming in-house custom Machine Learning Silicon. This role requires a deep understanding of neural network architecture, compilers, and the mapping of various operations onto the hardware. The ideal candidate is an experienced machine learning engineer with a strong understanding of GPUs and AI accelerators, and is comfortable working rapidly in a small-team environment. You will be expected to analyze and deploy state-of-the-art neural networks on GPU and AI accelerators, while also developing ML compiler support for new hardware features. Building high-level performance models and analyzing performance will be a key part of your responsibilities, as well as proposing new hardware features backed by performance estimates. Debugging performance bottlenecks and issues in hardware or simulation will also be a critical aspect of your role.