AMD - San Jose, CA
posted 2 months ago
At AMD, we are committed to transforming lives through our technology, and we are looking for a Principal Machine Learning Performance Engineer to join our team. This role is pivotal in focusing on ML performance modeling, projection, and optimization for various machine learning workloads. You will engage in hardware and software co-design, emphasizing the interaction between ML workloads and hardware architecture. Your work will involve modeling workloads, including generative AI models across multiple hardware configurations, and summarizing your recommendations based on your findings. You will collaborate closely with both customers and the business unit to project performance, analyze results, and develop solutions that meet customer needs. If you are passionate about performance optimization and shaping the future of AI acceleration, this role is tailored for you. As a Machine Learning Performance Engineer, you will delve into recent ML models, analyzing their compute and memory requirements to provide projections on various compute hardware for both inference and training. Your role will also involve identifying innovative ways to enhance performance. The ideal candidate will possess strong experience in ML hardware architecture, software optimization, and performance modeling, making them a key player in our mission to build great products that accelerate next-generation computing experiences.