Compiler Engineer, AI ML Models on Neuron

Amazon; Cupertino (CA); On-site; USD 126,000 - 171,000; Full time

Job summary

Amazon in Cupertino, CA is seeking a software engineer for the AWS Neuron compiler team. You will design, implement, test, deploy and maintain software to optimize the Neuron compiler's performance for ML models on AWS Inferentia and Trainium.

You will collaborate with chip architects and ML teams to deliver state-of-the-art compiler features, with opportunities to work on open-source projects like StableHLO, OpenXLA, and MLIR, while engaging in pre-silicon design and rapid feature delivery.

Qualifications

• 1+ years of non-internship design or architecture experience
• 3+ years of full software development life cycle experience
• Bachelor's degree in computer science or equivalent

Responsibilities

• Design, implement, test, deploy and maintain innovative software solutions to transform Neuron compiler's performance, stability and user-interface
• Collaborate with chip architects, runtime/OS engineers, scientists and ML Apps teams to deploy ML models on AWS accelerators with cost/performance benefits
• Work with open-source software (StableHLO, OpenXLA, MLIR) to optimize ML workloads on AWS software and hardware
• Contribute to building features that deliver best possible experiences for developers

Skills

Programming experience

System design

Communication

Education

Bachelor's degree in computer science or equivalent

Job description

Amazon in Cupertino, CA is seeking a software engineer for the AWS Neuron compiler team. You will design, implement, test, deploy and maintain software to optimize the Neuron compiler's performance for ML models on AWS Inferentia and Trainium.

You will collaborate with chip architects and ML teams to deliver state-of-the-art compiler features, with opportunities to work on open-source projects like StableHLO, OpenXLA, and MLIR, while engaging in pre-silicon design and rapid feature delivery.