AWS Machine Learning accelerators are at the forefront of AWS innovation. The Inferentia and Trainium chips deliver industry-leading ML inference and training performance at the lowest cost in the cloud. This is all enabled by edge software stack, the AWS Neuron Software Development Kit (SDK), which includes an ML compiler and runtime and natively integrates into popular ML frameworks, such as PyTorch, JAX, TensorFlow and MxNet. AWS Neuron is widely adopted by customers and partners like PyTorch, Epic Games, Snap, Airbnb, Autodesk, Alexa, and Rekognition. Amazon Annapurna Labs drives innovation in silicon and software for AWS, blending cloud-scale impact with world-class engineering talent. Our multidisciplinary team spans silicon design, hardware verification, software, and operations. We operate in large, complex domains with small, agile teams, fostering continuous learning and rapid innovation. With no set blueprint, we thrive on experimentation and offer a uniquely dynamic and enriching environment across a wide range of AWS products and services. We are seeking an accomplished Software Engineering Manager with strong leadership and mentoring capabilities to join our Deep Learning Compiler team. In this Manager III role, you will lead a team of seasoned compiler and software engineers in the design and development of a machine learning compiler simulator and verifier. The simulator simulates the model execution at different stages of compilation, targeting AWS Inferentia and Trainium chips. The verifier statically checks for correctness and key conditions within the compilation process, enabling early detection and prevention of failures. Together, they play a critical role in enhancing development efficiency, streamlining debugging, and enabling rapid prototyping. You need to be technically capable, credible, and curious in your own right as a trusted AWS Neuron Manager, innovating on behalf of our customers. You will leverage your technical skills as a hands-on partner to AWS ML services teams, involved in pre-silicon design, bringing new products/features to market.