Who you are

- Bachelor's degree in Computer Science, Engineering, Mathematics, or a related field

- 3+ years of non-internship professional software development experience

- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of recent and existing systems experience

- Experience programming with at least one software programming language

- 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

- Experience working with PyTorch or JAX software

- Experience with Machine Learning and Large Language Model fundamentals, including architecture, training/inference lifecycles, and optimization of model execution

- Experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware

What the job involves

- The Neuron Explorer team makes AWS Trainium performance visible. We own Neuron Explorer, the tool for profiling, debugging, and optimizing machine learning workloads on Trainium and Inferentia. We build profiling, debugging, and analysis tools that let engineers see how efficiently models and kernels use the hardware, pinpoint bottlenecks, and decide what to optimize next

- Neuron Explorer traces execution from source code down to hardware operations across both single-node and distributed applications. Our goal is to cut through complex execution data so customers can optimize faster and reach higher performance on Trainium





- As the Software Development Engineer for the Neuron Explorer team, you will design, build, and operate the full stack behind Neuron Explorer — from low-level performance data collection and analysis engines to interactive visualizations and developer workflows

- You will own features end to end, spanning the backend processing pipeline, the web UI, and the CLI, and you will help push our AI-powered recommendation and analysis capabilities that automatically surface bottlenecks and guide optimization

- Design and build performance data collection pipelines and analysis engines that transform raw hardware execution data into actionable insights for Neuron Explorer users

- Develop interactive visualizations and developer workflows that make complex profiling data understandable, helping customers pinpoint bottlenecks across single-node and distributed training workloads

- Own features end to end across the full software development lifecycle — from scoping and design through implementation, testing, deployment, and operations — ensuring reliability and maintainability

- Collaborate with compiler, runtime, and chip architecture teams to surface the right performance information so internal and external customers can optimize AI workloads on Trainium and Inferentia hardware

- Evaluate and integrate generative AI capabilities into Neuron Explorer's recommendation engine, building features that automatically identify optimization opportunities and guide customers toward higher performance

📌 Software Development Engineer (Toronto)
🏢 Amazon
📍 Toronto