ML Compiler Engineer for Custom ML Accelerators

Amazon; Cupertino (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Amazon is seeking a software engineer for the Neuron compiler team in Cupertino to design and implement the next‑generation Neuron compiler. You will translate models from PyTorch, TensorFlow, and JAX into efficient code for Inferentia/Trainium chips, collaborating with cross‑domain teams to optimize ML workloads.

The role requires strong OO language skills (C++/Java), system design experience, and a Master’s/PhD in CS preferred.

Qualifications

• 3+ years of professional software development experience.
• 2+ years of system design or architecture experience.
• Proficiency in at least one object‑oriented language such as C++ or Java.

Responsibilities

• Design, implement, test, deploy and maintain the Neuron compiler to improve performance, stability, and usability.
• Partner with chip architects, runtime/OS engineers, scientists, and ML application teams to deliver optimized ML workloads on AWS accelerators.
• Develop compiler optimization and verification passes that support large‑scale models, including LLMs, vision transformers, and stable diffusion.
• Integrate open‑source tools such as OpenXLA, StableHLO, and MLIR to advance compiler capabilities.
• Build tools for numerical‑error analysis, defect resolution, and performance profiling.

Skills

C++/Java

System design

OOP

Education

Master’s degree or PhD in CS

Tools

OpenXLA

StableHLO

MLIR

LLVM

Bazel

CMake

Job description

Amazon is seeking a software engineer for the Neuron compiler team in Cupertino to design and implement the next‑generation Neuron compiler. You will translate models from PyTorch, TensorFlow, and JAX into efficient code for Inferentia/Trainium chips, collaborating with cross‑domain teams to optimize ML workloads.

The role requires strong OO language skills (C++/Java), system design experience, and a Master’s/PhD in CS preferred.