AI GPU Performance Engineer Job

Will contribute to the development of MAX Engine, Modular’s framework that allows Modular clients to deploy AI models in the Cloud or on their local servers; primarily focus on optimizing MAX’s performance across different hardwares including central processing units (CPUs) and GPUs, with the aim to reduce latency and server costs for our customers; will specialize in writing and tuning low-level software building blocks, known as kernels which are responsible for performing basic mathematical operations, such as matrix multiplications, in all AI models; will use Mojo, Modular’s high-performance programming language, to write these kernels; will ensure that with optimized kernels, the AI models run with minimal latency, which translates into faster responses time for end users.

Master's degree in Computer Science, Physics or related field required.

Please mail resume and application to our company address at Modular, Inc., 199 1st Street, Suite 200 (Box 1), Los Altos, CA 94022, Attention: Liz Rojas.

Technology