AWS Machine Learning accelerators are revolutionizing cloud computing with custom silicon chips - Inferentia for ML inference and Trainium for ML training. These are powered by the AWS Neuron SDK, featuring a deep learning compiler and runtime with native integration for popular ML frameworks. The Tel Aviv team will be crucial in developing the Neuron compiler stack, translating neural network models into high-performance execution on AWS custom hardware.
As a Senior Machine Learning Compiler Engineer, you'll join Amazon Annapurna Labs' AWS Neuron team, working across software, hardware, and silicon engineering. You'll lead compiler technology development, optimize ML workloads, and contribute to hardware development from pre-silicon design through production deployment. The role offers opportunities to influence architecture, mentor engineers, and collaborate with AWS service teams.
The position requires strong technical leadership, with responsibilities including architecting critical features, publishing research, and mentoring experienced engineers. You'll work closely with AWS ML services teams and contribute to various stages of product development. While ML and AI accelerator experience is preferred, the role primarily seeks innovative engineers passionate about scaling complex systems.
This is a founding team position in Tel Aviv, offering the unique opportunity to shape both technical direction and team culture while contributing to AWS's global ML infrastructure. The work directly impacts major customers like Snap, Autodesk, and Amazon's own services, making it an excellent opportunity for engineers looking to make a significant impact in the ML/AI infrastructure space.