AWS Neuron is seeking a Senior Software Development Manager to lead their ML compiler team, focusing on developing cutting-edge solutions for AWS Machine Learning accelerators. The role is situated within Amazon's Annapurna Labs, a team at the forefront of silicon and software innovation for AWS customers.
The position involves leading a team of compiler engineers working on AWS Inferentia and Trainium, AWS's proprietary ML acceleration chips. These technologies deliver best-in-class ML inference and training performance in the cloud. The Neuron SDK, which includes an ML compiler, runtime, and integrations with popular ML frameworks like PyTorch and TensorFlow, is a crucial part of this ecosystem.
The ideal candidate will bring deep expertise in compiler development, with strong knowledge of resource management, scheduling, code generation, and optimization. They'll need to demonstrate both technical excellence and leadership capabilities, with 6+ years of engineering team management experience and 8+ years of direct engineering team experience.
Key responsibilities include leading compiler development, partnering with AWS ML services teams, participating in pre-silicon design, and bringing new features to market. The role offers the opportunity to work with high-profile customers and partners, including PyTorch, Epic Games, Snap, and Amazon's own services like Alexa and Rekognition.
The position offers competitive compensation ranging from $198,100 to $342,300 based on location, plus additional benefits including equity and comprehensive medical coverage. The team emphasizes work-life balance, offering flexible working hours and a supportive, inclusive culture with strong emphasis on mentorship and career growth.
This is an exciting opportunity to shape the future of ML acceleration at AWS, working with a talented team that combines deep technical expertise with a culture of innovation and customer focus. The role requires a blend of technical depth, leadership skills, and strategic thinking to drive the evolution of AWS's ML infrastructure.