ML Compiler Engineer - Optimize Cutting-Edge DL Stacks

Amazon; Cupertino (CA); On-site; USD 143,700 - 194,400; Full time

Benefits offered by this job

Sign-on payments

Restricted stock units (RSUs)

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Amazon in Seattle, WA is seeking a skilled compiler engineer to design, develop, and optimize the AWS Neuron compiler stack, collaborating with ML accelerators such as Inferentia and Trainium. This role offers the chance to shape a state-of-the-art stack powering Generative AI across frameworks like PyTorch, TensorFlow, and JAX.

The engineer will collaborate with Runtime, Frameworks, and Hardware teams to deliver performance improvements and scalable solutions for large language models and

Qualifications

• Bachelor's degree in CS, engineering, mathematics, or related field.
• 3+ years of professional software development experience (non-internship).
• Proficiency with C++ and at least one ML framework.

Responsibilities

• Design, develop, and optimize features for the compiler stack.
• Work across Runtime, Frameworks, and Hardware teams to improve system-wide performance.
• Implement, test, and maintain software that improves service performance, durability, cost, and security.
• Contribute to design discussions and code reviews.

Skills

C++

Optimization algorithms

Graph theory

FPGA placement and routing

Hardware bring-up

TensorFlow

PyTorch

JAX

LLVM/MLIR

Experience with large-language models/

Education

Bachelor's degree in Computer Science, Engineering, Mathematics, or a related field

MS or Ph.D. in computer science or a related field

Tools

LLVM

MLIR

TensorFlow

PyTorch

JAX

Job description

Amazon in Seattle, WA is seeking a skilled compiler engineer to design, develop, and optimize the AWS Neuron compiler stack, collaborating with ML accelerators such as Inferentia and Trainium. This role offers the chance to shape a state-of-the-art stack powering Generative AI across frameworks like PyTorch, TensorFlow, and JAX.

The engineer will collaborate with Runtime, Frameworks, and Hardware teams to deliver performance improvements and scalable solutions for large language models and