Joblaze summary

In the role of TPU Kernel Engineer at Anthropic, the individual will focus on diagnosing and resolving performance challenges in various machine learning systems, particularly through the design and optimization of TPU kernels. Proficiency in optimizing ML systems for accelerators like TPUs and GPUs is essential, along with a strong background in large-scale systems and low-level optimization. This position is well-suited for experienced engineers who are results-driven and eager to engage in collaborative programming. Anthropic emphasizes a cohesive team environment, prioritizing impactful AI research with significant societal implications.

Joblaze insights

Listed about 6 months ago — first seen on Joblaze April 14, 2026. Last confirmed on Anthropic's careers page October 26, 2026.
Salary band is above the typical range for AI/ML roles (median ~$190,000).
Starts above 100% of 11 comparable senior ai/ml roles in United States that list GPU we track (median $215,000 across 6 companies).
GPU appears in 2.7% of 551 comparable senior ai/ml roles in United States; TPU appears in 0.4% of 551 comparable senior ai/ml roles in United States.

Quick facts

Is the TPU Performance Engineer role remote?: It's hybrid — Anthropic expects some on-site time in San Francisco, CA | New York City, NY | Seattle, WA.
What's the salary range?: Anthropic lists $280,000–$850,000 for this role.
Where is the role based?: Anthropic is hiring for this position in San Francisco, CA | New York City, NY | Seattle, WA.
What's the tech stack?: Joblaze extracted these technologies from the posting: Computer Architecture, GPU, Large Language Models, ML systems, TPU, Transformers.
Does Anthropic sponsor work visas for this role?: Yes — the posting indicates visa sponsorship is available for the right candidate.
What seniority level is this role?: Anthropic targets senior candidates for this position.
Is this full-time or contract?: Full-time for this TPU Performance Engineer role at Anthropic.

From the original posting

About Anthropic

About the Role

As a TPU Performance Engineer, you'll be responsible for identifying and addressing performance issues across many different ML systems, including research, training, and inference. A significant portion of this work will involve designing and optimizing kernels for the TPU. You will also provide feedback to researchers about how model changes impact performance. Strong candidates will have a track record of solving large-scale systems problems and low-level optimization.

You may be a good fit if you:

Have significant experience optimizing ML systems for TPUs, GPUs, or other accelerators
Are results-oriented, with a bias towards flexibility and impact
Pick up slack, even if it goes outside your job description
Enjoy pair programming (we love to pair!)
Want to learn more about machine learning research
Care about the 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
Understanding accelerators at a deep level, e.g. a background in computer architecture
ML framework internals
Language modeling with transformers

Representative projects:

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

The annual compensation range for this role is listed below.

Annual Salary:

$280,000—$850,000 USD

Logistics

Standard company text repeated across Anthropic's postings is omitted here.

TPU Performance Engineer