ML Compiler Engineer - Optimize DL Stack for Fast Inference

Amazon Web Services (AWS); Cupertino (CA); On-site; USD 150,000 - 200,000; Full time

Job summary

AWS in Cupertino seeks a skilled compiler engineer to help build a state‑of‑the‑art deep learning compiler stack for PyTorch, TensorFlow, and JAX across LLMs and vision. You’ll work with Inferentia/Trainium accelerators and influence system‑level performance optimization.

Responsibilities include designing and optimizing compiler features, tackling scheduling, memory, and graph challenges, and collaborating with Runtime, Frameworks, and Hardware teams to deliver end‑to‑end improvements for

Qualifications

• Bachelor’s degree in CS/Engineering or related field required.
• Minimum 3+ years of professional software development experience.
• Proficiency in C++ and programming languages; strong optimization skills.
• 2+ years in optimization algorithms, graph theory, or hardware bring‑up.

Responsibilities

• Design, develop, and optimize compiler features for deep learning models.
• Address challenges from instruction scheduling to code generation across the stack.
• Collaborate with Runtime, Frameworks, and Hardware teams for end‑to‑end improvements.
• Research and implement solutions for best customer experience.
• Participate in design reviews, code reviews, and cross‑functional decisions.

Skills

C++

Optimization

Graph theory

Hardware bring-up

Parallel programming

Education

Bachelor's degree in CS/Engineering

Tools

LLVM/MLIR

Job description

AWS in Cupertino seeks a skilled compiler engineer to help build a state‑of‑the‑art deep learning compiler stack for PyTorch, TensorFlow, and JAX across LLMs and vision. You’ll work with Inferentia/Trainium accelerators and influence system‑level performance optimization.

Responsibilities include designing and optimizing compiler features, tackling scheduling, memory, and graph challenges, and collaborating with Runtime, Frameworks, and Hardware teams to deliver end‑to‑end improvements for