TPU Kernel & Performance Engineer

Anthropic Limited; New York (NY); On-site; USD 280,000 - 850,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching

Generous vacation & parental leave

Flexible working hours

Office space in San Francisco

Job summary

Anthropic is seeking a TPU Performance Engineer to identify and address performance issues across ML systems, including research, training, and inference. You will design and optimize kernels for the TPU and provide feedback to researchers on model performance impacts.

The role requires experience optimizing ML systems for TPUs/GPUs or accelerators, solving large-scale systems problems, and low-level optimization. We value collaboration and a passion for safe AI.

Qualifications

• Experience optimizing ML systems on TPUs/GPUs or accelerators.
• Track record solving large-scale systems problems and low-level optimization.

Responsibilities

• Identify and address performance issues across ML systems.
• Design and optimize kernels for the TPU.
• Provide feedback to researchers on how model changes impact performance.
• Debug kernel performance at the assembly level.

Skills

TPU optimization

GPU optimization

pair programming

ML research

systems optimization

Job description

Anthropic is seeking a TPU Performance Engineer to identify and address performance issues across ML systems, including research, training, and inference. You will design and optimize kernels for the TPU and provide feedback to researchers on model performance impacts.

The role requires experience optimizing ML systems for TPUs/GPUs or accelerators, solving large-scale systems problems, and low-level optimization. We value collaboration and a passion for safe AI.