Software Engineer, Neuron Compiler for ML Accelerators

Amazon Inc.; Cupertino (CA); In loco; USD 165.000 - 224.000; Tempo pieno

Descrizione del lavoro

Amazon Inc. in Los Angeles/California area is seeking a Software Development Engineer for the AWS Neuron compiler team. You will help transform ML models from frameworks like PyTorch, TensorFlow, and JAX to run efficiently on AWS Inferentia and Trainium chips in the cloud.

The role emphasizes compiler optimization, collaboration with hardware and software teams, and involvement with open-source toolchains such as StableHLO, OpenXLA, and MLIR. Prior OO language experience is required.

Competenze

• Three+ years of professional software development experience.
• Two+ years in design or architecture of subsystems and services.
• Three+ years of programming in languages like Java, C++, or C#, with OO design experience.

Mansioni

• You will design, implement, test, deploy and maintain software to optimize the Neuron compiler’s performance and reliability.
• You’ll collaborate with chip architects, runtime engineers, scientists, and ML Apps teams to deploy models on AWS accelerators.
• Work with open-source tools (StableHLO, OpenXLA, MLIR) to optimize ML workloads on AWS hardware.

Descrizione del lavoro

Amazon Inc. in Los Angeles/California area is seeking a Software Development Engineer for the AWS Neuron compiler team. You will help transform ML models from frameworks like PyTorch, TensorFlow, and JAX to run efficiently on AWS Inferentia and Trainium chips in the cloud.

The role emphasizes compiler optimization, collaboration with hardware and software teams, and involvement with open-source toolchains such as StableHLO, OpenXLA, and MLIR. Prior OO language experience is required.