ML Compiler Engineer for Custom AI Accelerators

Amazon Inc.; Cupertino (CA); On-site; USD 165,000 - 224,000; Full time

Job summary

Amazon is seeking a software engineer for the AWS Neuron compiler team in Cupertino. You will design, implement, test, and maintain software that optimizes the Neuron compiler for deploying ML models on AWS Inferentia and Trainium servers in the cloud.

You will work with chip architects, runtime/OS engineers, and ML teams, leveraging OpenXLA/StableHLO/MLIR to drive performance and ease of use, while engaging with open-source communities and customers.

Qualifications

• 3+ years of non-internship professional software development experience.
• 2+ years of design/architecture experience for new/existing systems.
• Experience programming with at least one software programming language.

Responsibilities

• Design, implement, test, deploy and maintain software to enhance Neuron compiler performance and stability.
• Collaborate with chip architects, runtime/OS engineers, scientists and ML Apps teams to optimize ML workloads on AWS accelerators.
• Explore open-source toolchains like StableHLO/OpenXLA/MLIR to advance compiler optimizations.

Skills

Software development

System design/architecture

Programming languages

Education

Master’s or PhD in CS or related field

Tools

OpenXLA

StableHLO

MLIR

PyTorch

JAX

TVM

Job description

Amazon is seeking a software engineer for the AWS Neuron compiler team in Cupertino. You will design, implement, test, and maintain software that optimizes the Neuron compiler for deploying ML models on AWS Inferentia and Trainium servers in the cloud.

You will work with chip architects, runtime/OS engineers, and ML teams, leveraging OpenXLA/StableHLO/MLIR to drive performance and ease of use, while engaging with open-source communities and customers.