jobs
ML Compiler Engineer, Neuron Kernel Interface
AWS Machine Learning accelerators are at the forefront of AWS innovation. Trainium delivers best-in-class ML training performance with the most teraflops (TFLOPS) of compute power for ML in the cloud.
En inglés
- Company
- Amazon
- Location
- Seattle, Washington, USA
- Status
- Closed
- Posted
- 2026-10-17
Amazon's Annapurna Labs is hiring an ML compiler engineer for the AWS Neuron team in Seattle. The role involves building compiler features for Trainium, from frontend and intermediate representations through optimization and code generation. Responsibilities include testing on hardware and simulation, supporting Amazon ML teams using PyTorch and JAX, reviewing code, and mentoring newer engineers. The posting asks for at least three years of professional software development and C++ or similar experience. It stands out for direct work on a bare-metal kernel language and compiler tied to custom ML silicon.
Original job posting