Senior ML Accelerator Runtime Engineer

Amazon

Seattle (WA)

On-site

USD 143,700 - 194,400

Full time

14 days+

Application generator

An application made for this job — a tailored resume and cover letter that speak straight to the posting.

Get past ATS filters

Benefits offered by this job

Health insurance

Dental

Vision

RSUs

401(k) matching

Paid time off

Parental leave

Job summary

Amazon is seeking a Software Development Engineer for the AWS Neuron Runtime Team to build and maintain high‑performance runtime libraries and drivers for AI accelerators such as Inferentia and Trainium. You will design, develop, and deploy Neuron Runtime and other Neuron components, and contribute to profiling to optimize AI workloads across devices.

You will work with cross‑functional teams to enable performance insights, own end‑to‑end services, and participate in post‑incident reviews while

Qualifications

3+ years of professional software development experience.
2+ years of design or architecture experience focusing on reliability and scaling.
Experience programming in at least one software programming language.

Responsibilities

Design, develop, and deploy high‑performance runtime libraries and drivers for AI accelerators.
Develop and maintain the Neuron Runtime, ensuring scalability, reliability, and usability across services.
Collaborate with cross‑functional teams to generate key information in a C++ compiler that enables customers to understand and optimize performance.
Drive innovation to support multiple machine‑learning frameworks (PyTorch, JAX, XLA) in the profiler.
Own services end‑to‑end, including deployment, monitoring, alarming, on‑call responsibilities, and post‑incident reviews.
Work with executive leadership and senior technical leaders to define product directions and deliver solutions at scale.