Software Compiler Engineer for Neuron MLIR/OpenXLA

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

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Job summary

Amazon is recruiting a Software Development Engineer for the AWS Neuron team (Annapurna Labs) in Cupertino. You will design and implement compiler optimizations to transform ML models for Inferentia and Trainium accelerators, collaborating with chip architects and ML teams to deliver high-performance software.

The role emphasizes building scalable compiler passes, integrating open-source toolchains, and delivering user-friendly features for developers deploying diverse ML workloads in AWS.

Qualifications

• 3+ years of non-internship professional software development experience.
• 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems.
• Experience programming with at least one software programming language.

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 models on AWS accelerators with optimal cost/performance benefits.
• Work with open-source tools like StableHLO, OpenXLA, MLIR to optimize ML workloads on AWS.

Skills

3+ years software development

2+ years design/architecture

Programming language

Education

Master's/PhD in CS

Tools

OpenXLA

StableHLO

MLIR

LLVM

Job description

Amazon is recruiting a Software Development Engineer for the AWS Neuron team (Annapurna Labs) in Cupertino. You will design and implement compiler optimizations to transform ML models for Inferentia and Trainium accelerators, collaborating with chip architects and ML teams to deliver high-performance software.

The role emphasizes building scalable compiler passes, integrating open-source toolchains, and delivering user-friendly features for developers deploying diverse ML workloads in AWS.