Description
The AWS Neuron Kernel Engineer will design and implement high-performance compute kernels for machine learning operations on AWS Inferentia and Trainium accelerators, optimize kernel-level performance across hardware generations, use profiling tools to resolve bottlenecks, apply compiler optimizations such as fusion, sharding, tiling, and scheduling, and work with customers to enable and optimize ML models. The role also involves cross-functional collaboration, customer support, technical design, code review, and mentoring experienced engineers. It requires substantial engineering management, software architecture, web services, and full software/hardware/networks development experience, and is based in Toronto with a listed annual salary range of CAD 171,400 to 286,200.
