Staff Engineer, Inference Runtime — High-Performance AI Serving

Anthropic; Seattle (WA); Hybrid; USD 405,000 - 485,000; Full time

Job summary

Anthropic is looking for a Staff Engineer to lead the Inference Runtime team in Seattle, WA. You will oversee the architecture and roadmap for inference serving systems, ensuring performance and correctness across GPU, TPU, and Trainium platforms.

The ideal candidate will have a strong background in systems engineering and software development. Familiarity with high-performance distributed systems and mentoring experience is crucial. This is a hybrid position with a salary range of $405,000—$485,000.

Qualifications

• Deep background in systems engineering or ML infrastructure.
• Real depth in at least one accelerator ecosystem (CUDA/GPU, TPU, or Trainium).
• Experience with high-performance distributed systems.
• Track record of using engineering metrics for improvements.
• Strong communication skills to influence technical direction.

Responsibilities

• Set technical direction and architecture for the inference serving stack.
• Own and evolve the runtime’s interfaces and structure.
• Drive efficient accelerator usage across different platforms.
• Mentor engineers through design and code reviews.

Skills

Systems engineering

ML infrastructure

Performance profiling

Latency optimization

Software engineering experience

Technical alignment

Education

Bachelor’s degree or equivalent

Tools

CUDA/GPU

TPU

Rust

Python

Kubernetes

Job description

Anthropic is looking for a Staff Engineer to lead the Inference Runtime team in Seattle, WA. You will oversee the architecture and roadmap for inference serving systems, ensuring performance and correctness across GPU, TPU, and Trainium platforms.

The ideal candidate will have a strong background in systems engineering and software development. Familiarity with high-performance distributed systems and mentoring experience is crucial. This is a hybrid position with a salary range of $405,000—$485,000.