Amazon
Machine Learning - Compiler Engineer , AWS Neuron, Annapurna Labs
$165K–$224K
Cupertino, CA · Full-time · Posted Oct 6, 2026
- Experience
- 3+ years of non-internship professional software development; 2+ years of non-internship design or architecture experience. Preferred: 3+ years writing production-grade code in object-oriented languages such as C++/Java.
- Education
- Preferred: Master's degree or PhD in Computer Science or a related technical field.
About the job
Build and optimize the AWS Neuron compiler that converts machine-learning models for deployment on AWS Inferentia and Trainium accelerators.
What you'll do
- Design, implement, test, deploy, and maintain compiler software, including optimization and verification passes and tools for analyzing numerical errors.
- Improve compiler performance, stability, and usability for diverse ML workloads and resolve compiler defects.
- Collaborate with chip architects, runtime and OS engineers, scientists, ML application teams, customers, and open-source communities.
What they ask for
- 3+ years of non-internship professional software development experience.
- 2+ years of non-internship experience designing or architecting new and existing systems, including design patterns, reliability, and scaling.
- Experience programming in at least one software programming language.
Nice to have
- Master's degree or PhD in Computer Science or a related technical field; compiler design or production-grade C++/Java experience.
- Experience with LLVM/MLIR, PyTorch, OpenXLA, StableHLO, JAX, TVM, deep learning models and algorithms, or Bazel/CMake.
Pay
165,200.00 - 223,600.00 USD annually (base salary)
Tools
C++, Java, AWS Neuron, AWS Inferentia, Trainium, OpenXLA, StableHLO, MLIR
AI focus
Develop compiler optimizations for deep-learning models, including large language models, diffusion models, vision transformers, and multimodal models, targeting AWS accelerators.
Model-written summary · the original posting is authoritative