Senior Neuron Accelerator Performance Engineer
2 days ago
Winnipeg MB, Winnipeg Census Division, MB; Manitoba, Canada
Ml Jobs
Full-time
Free with email or Google
Save this job and keep your search organized
Create a free account to save jobs, create alerts and return to this listing from your dashboard.
Free with email or Google
By continuing, you agree to our Terms & Privacy Policy.
Build performance-critical software for Amazon Neuron, combining kernel optimization and system architecture for Inferentia and Trainium accelerators.
This senior engineering role sits within Annapurna Labs at Amazon and supports the Neuron software development kit. You will optimize workloads across multiple technology layers, including frameworks, compilers, runtime, and collectives. Your work will help customers enable models and improve performance on custom machine learning hardware.
Key Responsibilities
Craft compute kernels using Neuron architectures and programming modelsInvestigate bottlenecks through detailed performance profilingDevelop compiler optimizations for machine learning workloadsCollaborate with hardware, compiler, runtime, and framework teamsCommunicate with customers about model enablement and optimizationRequirements:
Five-plus years of full software development lifecycle experienceExperience with coding standards, reviews, testing, and operationsExperience leading design or architecture for scalable systemsMentoring, technical leadership, or engineering team leadership experienceBachelor's degree in computer science or equivalent preferredApply system architecture, profiling, and compiler optimization skills to advance Amazon's Neuron accelerator software.
#J-18808-Ljbffr
This senior engineering role sits within Annapurna Labs at Amazon and supports the Neuron software development kit. You will optimize workloads across multiple technology layers, including frameworks, compilers, runtime, and collectives. Your work will help customers enable models and improve performance on custom machine learning hardware.
Key Responsibilities
Craft compute kernels using Neuron architectures and programming modelsInvestigate bottlenecks through detailed performance profilingDevelop compiler optimizations for machine learning workloadsCollaborate with hardware, compiler, runtime, and framework teamsCommunicate with customers about model enablement and optimizationRequirements:
Five-plus years of full software development lifecycle experienceExperience with coding standards, reviews, testing, and operationsExperience leading design or architecture for scalable systemsMentoring, technical leadership, or engineering team leadership experienceBachelor's degree in computer science or equivalent preferredApply system architecture, profiling, and compiler optimization skills to advance Amazon's Neuron accelerator software.
#J-18808-Ljbffr