Senior AI/ML Software Engineer for Hardware Accelerators

Amazon; Seattle (WA); On-site; USD 168,000 - 227,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

RSUs

Job summary

Amazon in Seattle, WA is seeking a Sr. Software Engineer for AI/ML on AWS Neuron Apps to optimize large-scale models and accelerators. You will collaborate with silicon, compiler teams, and ML frameworks to push performance across inference workloads.

You will develop kernels, participate in end-to-end optimization from software to hardware, and mentor others while delivering scalable solutions for billions of inferences daily.

Qualifications

• 5+ years of full software development life cycle experience.
• 5+ years of programming experience using Python or C++ and PyTorch.
• Experience with AI acceleration via quantization, parallelism, model compression, and batching.

Responsibilities

• Build and scale distributed inference solutions for large language models.
• Collaborate with silicon Architects and compiler engineers to shape AI accelerators.
• Write custom kernels to optimize LLM computation graphs for latency and cost.
• Optimize models for Neuron hardware across languages and frameworks.

Skills

Python

C++

PyTorch

Distributed systems

ML optimization

Performance tuning

Education

Master's degree in computer science or equivalent

Master's degree in machine learning or equivalent

Tools

CUDA

HPC

Tensor operations

Job description

Amazon in Seattle, WA is seeking a Sr. Software Engineer for AI/ML on AWS Neuron Apps to optimize large-scale models and accelerators. You will collaborate with silicon, compiler teams, and ML frameworks to push performance across inference workloads.

You will develop kernels, participate in end-to-end optimization from software to hardware, and mentor others while delivering scalable solutions for billions of inferences daily.