Tech Stack

Description

You will focus on ML model deployment, integration, and optimization on embedded compute platforms for autonomous vehicles. You'll analyze ML workload performance, optimize models, and collaborate with deep learning experts to enable algorithms on GPU, NPU, and other accelerators.

Requirements

• Experience with ML accelerators (GPUs, NPUs, TPUs) and CUDA, TensorRT
• Strong C++ development in Linux environment
• Experience with parallel and high-performance computing
• Degree in Software Engineering, Computer Science, or equivalent experience
• Preferred: PyTorch, TensorFlow, ONNX, embedded ARM development, MLOps/DevOps

Responsibilities

• ML model deployment, integration, and optimization on embedded compute platforms
• Analyze ML workload performance on various hardware processors
• Design, develop, test, integrate, and optimize software on ML compute architectures
• Collaborate with deep learning experts to enable algorithms on GPU/NPU architectures
• Lead designs to determine system needs and improve ML software stack