ML Compiler Engineer, Annapurna Labs

The AWS Neuron Compiler team is seeking skilled compiler engineers to develop a state-of-the-art deep learning compiler stack. This role focuses on optimizing application models across diverse domains, including Large Language and Vision, working with frameworks like PyTorch, TensorFlow, and JAX. As an ML Compiler engineer at Annapurna Labs, you'll work with custom-built Machine Learning accelerators (Inferentia/Trainium) and be instrumental in designing and developing compiler features.

The position involves collaboration with cross-functional teams to ensure system-wide performance optimization. You'll work on crucial aspects including instruction scheduling, memory allocation, data transfer optimization, graph partitioning, parallel programming, and hardware-software co-design. This is an opportunity to work with AWS's innovative custom chips and accelerators that enable cloud solutions previously thought impossible.

The role offers competitive compensation ($129,300-$223,600 based on location) and comprehensive benefits. You'll be part of AWS Utility Computing (UC), which provides foundational services like S3 and EC2, and continues to innovate in cloud computing. The team values knowledge-sharing, mentorship, and career growth, with a strong focus on work-life harmony and inclusive culture.

Key responsibilities include solving challenging technical problems, implementing innovative software solutions, and working in a startup-like environment where impact and customer focus are paramount. The position requires strong technical expertise in compiler design and optimization, with opportunities to work on cutting-edge ML hardware and software systems.