ML Kernel Performance Engineer for Neuron Accelerators

Amazon; Cupertino (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Amazon's Annapurna Labs in the AWS Neuron group seeks a dedicated ML Kernel Performance Engineer to design and optimize high-performance compute kernels for ML workloads on Inferentia and Trainium. You will push kernel optimization boundaries across generations and collaborate with cross-functional teams.

This role partners directly with customers to tune models for AWS accelerators, applies compiler optimizations, and participates in design reviews and code quality activities in a startup-like

Qualifications

• 3+ years of non-internship professional software development experience.
• 2+ years of non-internship design or architecture experience for new and existing systems.
• Experience programming with at least one software programming language.
• 3+ years of full software development life cycle experience, including coding standards, reviews, and operations.
• Bachelor’s degree in computer science or equivalent.

Responsibilities

• Design and implement high-performance compute kernels for ML operations leveraging the Neuron architecture.
• Analyze and optimize kernel-level performance across multiple generations of Neuron hardware.
• Conduct detailed performance profiling to identify bottlenecks and optimize them.
• Apply compiler optimizations such as fusion, tiling, and scheduling.
• Work directly with customers to enable and optimize ML models on AWS accelerators.

Skills

Software development

System design

Programming language

Education

Bachelor's degree in Computer Science

Job description

Amazon's Annapurna Labs in the AWS Neuron group seeks a dedicated ML Kernel Performance Engineer to design and optimize high-performance compute kernels for ML workloads on Inferentia and Trainium. You will push kernel optimization boundaries across generations and collaborate with cross-functional teams.

This role partners directly with customers to tune models for AWS accelerators, applies compiler optimizations, and participates in design reviews and code quality activities in a startup-like