Description:
What to Expect Our team productionalizes ML models - we train and deploy large neural networks for efficient inference on compute-constrained edge devices (CPU / GPU / AI ASIC). You will focus on neural network architecture co-design for neural networks that run on Autopilot and Optimus What You?ll Do Co-design state-of-the-art neural networks for deployment on heterogenous compute, including Tesla's in-house AI ASIC, with an aim to maximize network performance while minimizing latencyCollabora
Apr 12, 2024;
from:
dice.com