Tech Stack

Description

You will identify and address performance issues across ML systems, design and optimize kernels for TPUs, and provide feedback on how model changes impact performance. This role involves low-level optimization and collaboration with researchers.

Requirements

• Significant experience optimizing ML systems for TPUs, GPUs, or other accelerators
• Results-oriented with bias towards flexibility and impact
• Willingness to pair program
• Interest in machine learning research and societal impacts
• Bachelor's degree in relevant field

Responsibilities

• Identify and address performance issues across ML systems
• Design and optimize kernels for TPU
• Provide feedback to researchers on model performance impact
• Implement low-latency, high-throughput sampling for large language models
• Adapt existing models for low-precision inference