ML Kernel Engineer at Amazon Devices
Amazon • vancouver, Canada
Role Description
Accelerate cutting-edge edge AI with Amazon Devices as an ML Kernel Performance Engineer. Focus on optimizing CUDA and Triton kernels for peak efficiency and deployment.
At Amazon Devices, the AI Platform team leverages innovative compression technology for effective neural network applications. As an ML Kernel Performance Engineer, you'll collaborate with scientists and engineers to enhance the performance of GPU workloads. Your expertise will ensure significant performance enhancements during model training and inference, pushing the boundaries of edge AI capabilities.
Key Responsibilities:
• Design high-performance CUDA and Triton kernels for edge AI
• Optimize kernel performance for compression training workloads
• Implement operator fusion and memory access optimizations
• Develop tools to profile kernel efficiency and validate accuracy
• Collaborate on hardware-software integration and solutions
Requirements:
At Amazon Devices, the AI Platform team leverages innovative compression technology for effective neural network applications. As an ML Kernel Performance Engineer, you'll collaborate with scientists and engineers to enhance the performance of GPU workloads. Your expertise will ensure significant performance enhancements during model training and inference, pushing the boundaries of edge AI capabilities.
Key Responsibilities:
• Design high-performance CUDA and Triton kernels for edge AI
• Optimize kernel performance for compression training workloads
• Implement operator fusion and memory access optimizations
• Develop tools to profile kernel efficiency and validate accuracy
• Collaborate on hardware-software integration and solutions
Requirements: