Optimize machine learning kernels for Amazon Neuron using low-level performance analysis and accelerator expertise in Toronto, Ontario. As a Senior Machine Learning Kernel Engineer, you will develop high-performance kernels for Inferentia and Trainium accelerators. You will work across compiler, runtime, framework, and hardware teams. The work includes model enablement, profiling, compiler optimization, and customer support for machine learning workloads.
Key Responsibilities
Design high-performance kernels for machine learning operations Analyze performance across Neuron hardware generations Use profiling tools to resolve kernel bottlenecks Implement fusion, sharding, tiling, and scheduling optimizations Enable and optimize customer models on AWS accelerators
Requirements:
Five-plus years of skilled software development experience Five-plus years programming with a software language Five-plus years leading system design or architecture Experience mentoring or leading engineering teams Experience with accelerator architectures or GPU optimization Bring kernel development, compiler optimization, and machine learning acceleration expertise to Amazon Neuron in Toronto.