Senior ML Compiler Engineer – Build Next‑Gen ML on AI Accelerators

Amazon; Cupertino (CA); On-site; USD 193,300 - 261,500; Full time

Benefits offered by this job

Health benefits

401(k) matching

Parental leave

Job summary

Amazon's AWS Neuron team in Cupertino, CA seeks a senior software engineer to advance the next generation of a compiler transforming PyTorch, TensorFlow and JAX models into efficient deployments on Inferentia and Trainium servers.

As part of a startup‑like environment within AWS, you will design and implement optimization passes, collaborate across chip, runtime, and ML teams, and contribute to open‑source communities while mentoring others. Expect rigorous code reviews and robust testing.

Qualifications

• Bachelor's degree in computer science or equivalent.
• 5+ years of full software development life cycle experience.
• 3+ years of experience developing compiler features and optimizations.
• Proficiency in C++ or Python.

Responsibilities

• Design, implement, test, deploy, and maintain software for Neuron compiler performance, stability, and UI.
• Collaborate with chip architects, runtime/OS engineers, scientists, and ML teams on deployment of ML models.
• Represent the Neuron compiler in open-source communities (StableHLO, OpenXLA, MLIR) and engage with industry partners.
• Create compiler optimization and verification passes and tools for numerical error analysis.
• Resolve defects, participate in design reviews, and communicate with stakeholders via GitHub.
• Operate in a startup-like environment focused on critical development work.

Skills

Compiler development

C++

Python

Education

Bachelor's degree in Computer Science or equivalent

Tools

LLVM/MLIR

Job description

Amazon's AWS Neuron team in Cupertino, CA seeks a senior software engineer to advance the next generation of a compiler transforming PyTorch, TensorFlow and JAX models into efficient deployments on Inferentia and Trainium servers.

As part of a startup‑like environment within AWS, you will design and implement optimization passes, collaborate across chip, runtime, and ML teams, and contribute to open‑source communities while mentoring others. Expect rigorous code reviews and robust testing.