Description
Amazon is hiring a Senior Software Engineer for its Machine Learning Inference Applications team to develop and optimize core building blocks of large language model inference, including attention, MLP, quantization, speculative decoding, and mixture of experts, for AWS Neuron accelerators. The role collaborates with chip architects, compiler engineers, and runtime engineers to improve performance and accuracy across open-source and internally developed models. Candidates need at least five years of professional software development experience, five years of programming experience, five years of leading design or architecture, and experience mentoring, leading as a tech lead, or leading an engineering team. The position is based in Seattle, Washington, with a base salary of $168,100 to $227,400 annually.
