jobs

Sr. Software Development Engineer, Inference Team - AWS Neuron

AWS Neuron is the complete software stack for AWS Inferentia and Trainium, AWS purpose-built accelerators for cloud-scale machine learning. This senior software engineering role is part of the Machine Learning Inference Applications team an

Company

Amazon

Location

Seattle, Washington, USA

Status

Closed

Posted

2026-09-12T00:00:00+00:00

Amazon's AWS Neuron organization is hiring a senior software development engineer for its Machine Learning Inference Applications team in Seattle, on-site. The role centers on leading customization and optimization of open-source inference frameworks, including vLLM and SGLang, on Inferentia and Trainium accelerators — covering scheduling, model execution, kernel development, parallel computation, distributed KV cache and speculative decoding. It asks for five or more years of professional development, design leadership and mentoring experience, plus machine learning fundamentals. Preferred: PyTorch or JAX, accelerator deployment, and framework contributions.