Amazon
Overview
AWS Neuron Compiler team is seeking a compiler-skilled engineer to support the development and scaling of a compiler for the world's largest ML workloads on Annapurna Labs AI accelerators. The job involves architecting and implementing business-critical features, publishing cutting-edge research, and collaborating with AWS ML services teams. Some travel or relocation may be required to locations such as Cupertino (preferred), Seattle, or Toronto. Responsibilities
Innovating and delivering creative software designs to develop new services, solve operational problems, and improve developer velocity and operational safety Writing requirements documents, design documents, integration test plans, and deployment plans Communicating status and progress to schedule and sharing learnings with the team and stakeholders Basic Qualifications
To qualify, applicants should have earned (or will earn) a Bachelor's or Master's degree between December 2022 and September 2025 Proficiency in C++ and Python programming, applied to compiler projects Experience developing compiler optimizations or ML framework internals Preferred Qualifications
Knowledge of code generation, compute graph optimization, resource scheduling Experience optimizing TensorFlow, PyTorch or JAX deep learning models Experience with toolchains like LLVM, OpenXLA/XLA, MLIR, TVM Familiarity with CUDA programming for GPU acceleration About the Product and Team
The AWS Machine Learning accelerators (Inferentia/Trainium) enable high-performance ML inference and training. The Neuron SDK provides a compiler, runtime, and application framework integrated with ML frameworks like PyTorch. Annapurna Labs is the AWS infrastructure-focused organization that delivers silicon and software for AI workloads. The Neuron Compiler team works on a deep learning compiler stack to run state-of-the-art models on our accelerators. Location
Cupertino (preferred), Seattle, or Toronto. Candidates must be located or willing to relocate. Company/EEO
Amazon is an equal opportunity employer and does not discriminate on protected status. Our compensation reflects the cost of labor across US markets. Base pay ranges from $99,500/year to $200,000/year, with additional compensation components as applicable. This position will remain posted until filled. Referrals and other job postings may appear on the page, but only information relevant to this role is retained.
#J-18808-Ljbffr
AWS Neuron Compiler team is seeking a compiler-skilled engineer to support the development and scaling of a compiler for the world's largest ML workloads on Annapurna Labs AI accelerators. The job involves architecting and implementing business-critical features, publishing cutting-edge research, and collaborating with AWS ML services teams. Some travel or relocation may be required to locations such as Cupertino (preferred), Seattle, or Toronto. Responsibilities
Innovating and delivering creative software designs to develop new services, solve operational problems, and improve developer velocity and operational safety Writing requirements documents, design documents, integration test plans, and deployment plans Communicating status and progress to schedule and sharing learnings with the team and stakeholders Basic Qualifications
To qualify, applicants should have earned (or will earn) a Bachelor's or Master's degree between December 2022 and September 2025 Proficiency in C++ and Python programming, applied to compiler projects Experience developing compiler optimizations or ML framework internals Preferred Qualifications
Knowledge of code generation, compute graph optimization, resource scheduling Experience optimizing TensorFlow, PyTorch or JAX deep learning models Experience with toolchains like LLVM, OpenXLA/XLA, MLIR, TVM Familiarity with CUDA programming for GPU acceleration About the Product and Team
The AWS Machine Learning accelerators (Inferentia/Trainium) enable high-performance ML inference and training. The Neuron SDK provides a compiler, runtime, and application framework integrated with ML frameworks like PyTorch. Annapurna Labs is the AWS infrastructure-focused organization that delivers silicon and software for AI workloads. The Neuron Compiler team works on a deep learning compiler stack to run state-of-the-art models on our accelerators. Location
Cupertino (preferred), Seattle, or Toronto. Candidates must be located or willing to relocate. Company/EEO
Amazon is an equal opportunity employer and does not discriminate on protected status. Our compensation reflects the cost of labor across US markets. Base pay ranges from $99,500/year to $200,000/year, with additional compensation components as applicable. This position will remain posted until filled. Referrals and other job postings may appear on the page, but only information relevant to this role is retained.
#J-18808-Ljbffr