AL

Neuron Runtime Software Engineer

  • Annapurna Labs Inc.
  • Cupertino, United States
  • On-site
  • Full-Time
  • $143,700 - 223,600 per year
  • Posted yesterday
Other software

Salary: $143,700 - 223,600 per year

Requirements:

  • We need at least 3 years of non-internship professional software development experience.
  • We need at least 2 years of non-internship experience designing or architecting new and existing systems, with emphasis on design patterns, reliability, and scaling.
  • We require experience programming in at least one software language.
  • We prefer 3 years of full software development lifecycle experience, including coding standards, code reviews, source control management, build processes, testing, and operations.
  • We prefer a bachelors degree in computer science or an equivalent background.
  • We value experience architecting, building, and operating distributed systems with a focus on high availability and fault tolerance.
  • We value hands-on experience with AWS services in production, such as EC2, ECS, CloudWatch, S3, and Lambda.
  • We value a track record of owning services end to end, including deployment, monitoring, alerting, on-call support, and post-incident reviews.

Responsibilities:

  • We work alongside engineering peers to develop and maintain high-performance runtime libraries and drivers for machine learning applications and AI accelerators.
  • We design, build, deploy, and evolve Neuron Runtime and related Neuron components.
  • We improve the profiler to help customers optimize AI workloads on Trainium and Inferentia hardware by exposing performance bottlenecks and system behavior.
  • We enhance the performance of ML kernels and ML frameworks.
  • We manage the full development lifecycle of the Neuron Runtime, with an emphasis on scalability, reliability, and usability.
  • We collaborate with cross-functional teams so our C++ compiler produces the information customers need to analyze and optimize custom hardware performance.
  • We drive innovations that enable the profiler to support multiple frameworks, including PyTorch, JAX, and XLA.
  • We partner with executive leadership and senior technical leaders to define product direction and deliver it to customers.
  • We help build massive-scale distributed training and inference solutions.

Technologies:

  • AI
  • AWS
  • Lambda
  • Cloud
  • CloudWatch
  • EC2
  • Hardware
  • Support
  • Machine Learning
  • PyTorch
  • Flow

More:

We are AWS Neuron, the complete software stack for AWS Inferentia and Trainium cloud-scale machine learning accelerators, along with the servers that use them. Our team builds the full software, server, and chip stack that powers high-scale distributed training and inference. We foster an inclusive culture, supported by employee-led affinity groups, learning experiences, and leadership principles that encourage curiosity, diverse perspectives, and trust. We also prioritize work-life balance, flexible working hours, mentorship, and career growth. This role is based in the United States, with listed locations and salary ranges including Cupertino, CA and Seattle, WA. We offer comprehensive benefits such as health coverage, retirement matching, paid time off, parental leave, and additional support programs.

last updated 46 week of 2026

Apply on DevITjobs

You apply on DevITjobs, where this job was posted. Peter Nowak isn’t the employer and doesn’t check listings.

Get new jobs like this by email

Other software · United States

Free. Confirm by email first; unsubscribe anytime in one click.

Similar jobs

Neuron Runtime Software Engineer at Annapurna Labs Inc. — Cupertino, United States | Peter Nowak