Machine Learning Compiler Engineer, Annapurna Labs

Join the innovative team behind AWS Neuron Compiler, a cutting-edge deep learning compiler stack powering Generative AI and advanced ML workloads on AWS's custom-built ML accelerators — Inferentia and Trainium. Based in Tel Aviv, this role offers a unique opportunity to shape the future of AI infrastructure at AWS.

As a Machine Learning Compiler Engineer, you'll be part of a new core group driving innovation in compiler technology and systems-level ML software. You'll work at the intersection of machine learning and systems, tackling complex challenges in compiler optimization, hardware-software co-design, and performance optimization.

The role involves collaborating with diverse teams across AWS to impact our global customer base. You'll be solving unprecedented technical challenges at every stack layer, from instruction scheduling and memory management to graph partitioning and ISA design. The position offers a startup-like environment within AWS, where you'll always work on high-priority projects with direct customer impact.

The team is responsible for developing and maintaining the AWS Neuron Compiler, which is crucial for delivering best-in-class performance and cost-efficiency for ML inference and training in the cloud. You'll have the opportunity to work with cutting-edge technology while contributing to the future of cloud-based AI infrastructure.

This role combines deep technical expertise with collaborative teamwork, requiring both strong programming skills and the ability to work effectively across different teams and projects. You'll be involved in everything from detailed technical implementations to high-level architectural decisions, making this an excellent opportunity for someone passionate about both machine learning and systems engineering.