> Markdown version of [/jobs/ext/4343392-software-engineer-ai-ml-inference-team-aws-neuron](https://www.wearedevelopers.com/jobs/ext/4343392-software-engineer-ai-ml-inference-team-aws-neuron). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Software Engineer-AI/ML, Inference Team - AWS Neuron

- **Company:** Amazon.com, Inc.
- **Location:** Seattle, WA, United States
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Amazon Web Services, Cloud Computing, Code Review, Machine Learning, Open Source Technology, Performance Tuning, Software Engineering, Discretization, AWS Trainium, SGLang
- **Published:** October 26, 2026
- **Apply:** https://www.careerbuilder.com/job-details/software-engineer-ai-ml-inference-team-aws-neuron-seattle-wa--4101a5b6-d2d3-404b-a61c-568fe6223993

## About the Role

Software Engineering, Amazon Web Services (AWS), Artificial Intelligence (AI), Cloud Computing, Machine Learning, Amazon Web Services (AWS), Open Source, Performance Modeling, Performance Tuning/Optimization, Automation

## Description

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 build the serving technology that lets customers run large-scale model inference fast and efficiently on Neuron chips., As an engineer on this team, you"ll work on core serving technologies within open-source frameworks such as vLLM and SGLang, optimizing model serving performance on Neuron and broadening the range of models we support out of the box. Your work directly accelerates how quickly new models are enabled, shipped, and delivered to customers., * Contribute core serving features to open-source inference frameworks such as vLLM and SGLang - implementing and upstreaming support for continuous batching, paged attention, quantization, and distributed inference on Neuron.

 * Broaden the range of models supported out of the box, and build tooling and automation that shortens the path from a new model to a production-ready deployment.
 * Improve model development and shipping velocity by reducing enablement time for new models and strengthening the test, benchmarking, and release workflows the team relies on.
 * Collaborate with model development, performance, compiler, and runtime engineers to deliver end-to-end model performance - production-ready accuracy, scalability, and efficiency across a broad range of models and customer workloads.
 * Apply strong engineering practices - code reviews, testing, and operational excellence - to ship reliable, high-performance inference that customers depend on.