ML Kernel Performance Eng. Manager, Accelerators
Socket.dev
About Socket.dev
ML Kernel Performance Eng. Manager, Accelerators
Amazon in Toronto is seeking a senior ML kernel engineer to design and optimize high-performance compute kernels for AWS Neuron on Inferentia and Trainium accelerators. You will work across multiple generations, analyze bottlenecks, and collaborate with customers to enable optimized ML models.
The role combines ML, HPC, and distributed architectures, offering opportunities to mentor engineers, publish research, and drive kernel innovations for broad customer impact.
#J-18808-Ljbffr
