TPU Kernel Engineer

Anthropic is a public benefit corporation focused on creating reliable, interpretable, and steerable AI systems.

As a TPU Kernel Engineer, you will identify and address performance issues across ML systems, including research, training, and inference. A significant portion of the work involves designing and optimizing kernels for the TPU, and providing feedback to researchers on model performance impacts.

• Significant experience optimizing ML systems for TPUs, GPUs, or other accelerators
• Results-oriented with a bias towards flexibility and impact
• Comfortable picking up slack beyond job description
• Enjoy pair programming
• Interest in learning more about machine learning research
• Care about societal impacts of your work

Strong candidates may also have experience with high-performance large-scale ML systems, designing and implementing kernels for TPUs or other ML accelerators, deep understanding of accelerators (e.g., computer architecture), ML framework internals, and language modeling with transformers.

• Implement low-latency, high-throughput sampling for large language models
• Adapt existing models for low-precision inference
• Build quantitative models of system performance
• Design and implement custom collective communication algorithms
• Debug kernel performance at the assembly level

Annual salary range: $280,000—$850,000 USD.

Competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space.

Apply via the provided link.