ML Kernel Performance Engineer for Accelerators

Amazon in Toronto is seeking kernel engineers to optimize ML kernels for Neuron architecture and accelerate ML workloads on AWS accelerators. You will design high-performance compute kernels, analyze performance across generations, and work with customers to enable model acceleration.

The role offers a startup-like environment, opportunities to publish research, and mentorship within a diverse team, with a focus on performance tuning, collaboration, and innovation.