Neuron Runtime Engineer - ML Inference & Profiling

Amazon Web Services (AWS); Seattle (WA); On-site; USD 144,000 - 194,000; Full time

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Job summary

Annapurna Labs (U.S.) Inc. in Seattle, WA is seeking a Software Development Engineer for the Neuron Runtime Team.

You will build and maintain high‑performance runtime libraries and drivers for ML accelerators, and collaborate across teams to ensure the C++ compiler exposes key performance insights to customers. The role focuses on scalable distributed systems, profiling performance across Trainium and Inferentia devices, and integrating support for PyTorch, JAX, and XLA while owning deployment

Qualifications

• 3+ years of non‑internship professional software development experience.
• 2+ years of non‑internship design or architecture experience (design patterns, reliability, scaling).
• Experience programming with at least one software programming language.

Responsibilities

• Develop and maintain high‑performance runtime libraries and drivers for ML accelerators.
• Design, develop, and deploy Neuron Runtime and related components.
• Improve profiler to support multiple frameworks and optimize ML workloads.

Skills

Software development

System design

Programming language

Education

Bachelor's degree in computer science

Job description

Annapurna Labs (U.S.) Inc. in Seattle, WA is seeking a Software Development Engineer for the Neuron Runtime Team.

You will build and maintain high‑performance runtime libraries and drivers for ML accelerators, and collaborate across teams to ensure the C++ compiler exposes key performance insights to customers. The role focuses on scalable distributed systems, profiling performance across Trainium and Inferentia devices, and integrating support for PyTorch, JAX, and XLA while owning deployment