Logo
Amazon

Machine Learning Compiler Engineer, AWS Neuron

Amazon, Seattle, Washington, us, 98127

Save Job

Join the Annapurna Labs team at Amazon Web Services (AWS) as a Machine Learning Compiler Engineer, focusing on AWS Neuron, the software development kit designed to accelerate deep learning and GenAI workloads on Amazon's custom machine learning accelerators, Inferentia and Trainium. You will be part of the Acceleration Kernel Library team, dedicated to optimizing performance for AWS's cutting-edge ML accelerators. Working at the boundary of hardware and software, our engineers create high-performance kernels for ML functions, ensuring every operation counts in delivering top-notch performance for our customers' demanding workloads. In this role, you will leverage deep hardware knowledge combined with ML expertise as you push the boundaries of AI acceleration. The AWS Neuron SDK empowers developers to achieve unparalleled performance in ML inference and training, integrating seamlessly with popular frameworks like PyTorch. Your contributions will extend from compiling and optimizing existing performance to aiding in future architecture designs and working directly with customers to enable and optimize their models. **Key Responsibilities:** Design and implement high-performance compute kernels for ML operations. Analyze and optimize performance of kernels across multiple generations of Neuron hardware. Conduct in-depth performance analysis using profiling tools to identify and resolve bottlenecks. Implement compiler optimizations including fusion, sharding, tiling, and scheduling. Collaborate across teams to innovate kernel optimization techniques. Engage directly with customers to ensure optimal performance of their ML models on AWS accelerators. **As part of the team, your day-to-day activities will involve:** Creating metrics and implementing automation to improve software architecture. Building impactful solutions for a broad customer base. Participating in design discussions and code reviews. Working cross-functionally to influence business decisions with your technical expertise. Embracing a startup-like environment focused on delivering critical results. At AWS, we value diverse experiences and encourage all candidates to apply. Whether you're just starting your career or have an unconventional background, your unique perspective can contribute to our collaborative environment. We are committed to fostering an inclusive workplace that celebrates our differences and supports your growth through mentorship and professional development opportunities. Our team emphasizes work-life balance, providing flexibility in working hours to help you thrive both personally and professionally. About you: You should have at least 3 years of professional software development experience, along with 2 years of experience in design or architecture of systems. Proficiency in programming with at least one software language is essential. A Bachelor’s degree in Computer Science or a related field is preferred.