Develop AWS Neuron software for machine learning acceleration in Toronto, combining backend systems, web interfaces, CLI workflows, and performance analysis.
As a Senior Software Development Engineer, you will work on Neuron Explorer, which profiles, debugs, and analyzes workloads on Trainium and Inferentia. The role connects source code with hardware operations across single-node and distributed applications. You will help define product direction while delivering customer-facing capabilities.
Key Responsibilities:
- Design engines analyzing execution data from AI hardware
- Build backend, web UI, and CLI features
- Trace workloads across single-node and distributed applications
- Partner with compiler, runtime, and chip architecture groups
- Identify optimization opportunities with recommendation features
Requirements:
- Five or more years of qualified software development experience
- Experience as mentor, technical lead, or team leader
- Bachelor's degree in computer science or equivalent
- Machine learning and LLM architecture fundamentals preferred
- PyTorch, JIT, and AOT tracing experience preferred
Use machine learning and full-stack development skills to advance Neuron Explorer and performance optimization on AWS accelerators.