Sr. ML Compiler Engineer - Automated Reasoning Science, Annapurna Labs

The AWS Neuron Compiler team is seeking an experienced Sr. ML Compiler Engineer to join their cutting-edge efforts in developing a state-of-the-art deep learning compiler stack. This role is part of the Automated Reasoning Group, where you'll be working on optimizing application models across various domains, including Large Language Models and Vision, using frameworks like PyTorch, TensorFlow, and JAX.

The position involves working with AWS's custom-built Machine Learning accelerators, including Inferentia/Trainium, which are at the forefront of AWS's ML capabilities and power solutions like Generative AI. You'll be responsible for developing and maintaining critical tooling that ensures the highest standards of accuracy and reliability in the Neuron Compiler.

As a senior member of the team, you'll lead initiatives in building fuzzers and specification synthesis tooling for our LLVM-based compiler. The role requires strong software development skills in C++/Python and a deep understanding of compiler development. While a background in Machine Learning and AI accelerators is preferred, it's not mandatory.

The position offers competitive compensation ranging from $151,300 to $261,500 per year, depending on location, plus additional benefits including equity, sign-on payments, and comprehensive medical benefits. This is an excellent opportunity for someone passionate about compiler technology and machine learning to work on innovative solutions that power AWS's ML infrastructure.

The role is based in several key tech hubs - Seattle (preferred), Cupertino, Austin, or Toronto - offering flexibility in location while maintaining direct involvement with core AWS technology development. You'll be part of a team that values scientific rigor and innovation, working on projects that directly impact the performance and reliability of AWS's machine learning infrastructure.