Amazon
ML Compiler Engineer, Neuron Kernel Interface
$144K–$224K
Seattle, WA +1 · Full-time · Posted Oct 17, 2026
- Location
- Seattle, WA
Cupertino, CA - Experience
- 3+ years professional software development; 2+ years design or architecture; 1+ year software development engineer or related occupational experience; 1+ year large-scale software development using a listed language; 1+ year Object Oriented Design. Preferred: 3+ years full software development life cycle.
- Education
- Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field.
About the job
Develop and scale AWS Neuron compilers that compile machine-learning workloads for Trainium, from framework models to hardware-level kernels.
What you'll do
- Design, implement, test, and support compiler features across frontend, intermediate representations, optimization, and code generation.
- Work with Amazon ML teams to diagnose workloads and improve performance; provide compiler feedback to hardware teams.
- Review code and designs, and mentor newer engineers.
What they ask for
- 3+ years of non-internship professional software development experience; 2+ years of system design or architecture experience; and 1+ year of software development engineer or related occupational experience.
- At least 1 year developing large-scale software applications, tools, systems, or services using C#, C++, Java, or Perl.
- At least 1 year of Object Oriented Design experience and experience programming in at least one software language.
- Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field.
Nice to have
- 3+ years of full software development life cycle experience.
- Bachelor's degree in computer science or equivalent.
Pay
165,200.00 - 223,600.00 USD annually (base salary); 143,700.00 - 194,400.00 USD annually (base salary)
Tools
AWS Neuron, Neuron Kernel Interface (NKI), Trainium, PyTorch, JAX, C#, C++, Java
AI focus
Build compilers and kernels for machine-learning workloads on AWS Trainium, enabling model compilation and performance optimization.
Model-written summary · the original posting is authoritative