Ai Engineer • Senior

Who you are

You have significant experience optimizing machine learning systems for TPUs, GPUs, or other accelerators — your background includes a deep understanding of computer architecture and the internals of ML frameworks. You are results-oriented, with a bias towards flexibility and impact, and you enjoy collaborating with others through pair programming. You care about the societal impacts of your work and are eager to learn more about machine learning research. You have a track record of solving large-scale systems problems and low-level optimization, making you a strong candidate for this role.

Desirable

Experience with high-performance, large-scale ML systems and designing and implementing kernels for TPUs or other ML accelerators is a plus. Understanding accelerators at a deep level will help you excel in this position, as will familiarity with language modeling using transformers.

What you'll do

As a TPU Kernel Engineer at Anthropic, you will be responsible for identifying and addressing performance issues across various machine learning systems, including research, training, and inference. A significant portion of your work will involve designing and optimizing kernels specifically for TPUs. You will provide feedback to researchers about how model changes impact performance, ensuring that the systems you work on are efficient and effective. You will collaborate closely with a team of engineers and researchers, contributing to the development of reliable, interpretable, and steerable AI systems that align with Anthropic's mission.

What we offer

Anthropic is a public benefit corporation headquartered in San Francisco, offering competitive compensation and benefits, including optional equity donation matching, generous vacation and parental leave, and flexible working hours. You will have the opportunity to work in a lovely office space that fosters collaboration with colleagues who are equally committed to building beneficial AI systems. We encourage you to apply even if your experience doesn't match every requirement, as we value diverse perspectives and backgrounds in our team.