jobs
Software Engineer-AI/ML, 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. Join the Machine Learning Inference Applications team to…
En anglais
- Company
- Amazon
- Location
- Seattle, Washington, USA
- Status
- Closed
- Posted
- 2026-10-06
Amazon is hiring a software engineer for the Machine Learning Inference Applications team in AWS Neuron, Seattle, working on the serving stack for Inferentia and Trainium accelerators. The job centres on open-source inference frameworks like vLLM and SGLang: continuous batching, paged attention, quantization and distributed inference, plus tooling that speeds new models to production. The posting asks for three or more years of professional software development, design experience with large-scale distributed systems in C++, Java or C#, and transformer and LLM fundamentals. CUDA or Triton kernel work is preferred.
Original job posting