Staff Software Engineer - Scalable Inference Systems

Anthropic Limited; Seattle (WA); Hybrid; USD 320,000 - 485,000; Full time

Job summary

Anthropic Limited seeks an experienced Software Engineer to join the Inference team and scale Claude’s inference stack across multiple clouds and accelerators. You will design, deploy, and operate distributed, high‑performance systems; implement intelligent request routing, autoscaling, and production pipelines used by researchers and millions of users.

Compensation ranges from $320,000 to $485,000 USD per year.

Qualifications

• Significant software engineering experience with distributed systems.
• Results-oriented with a bias towards flexibility and impact.
• Willingness to pick up slack beyond the job description.
• Desire to learn more about machine learning systems and infrastructure.
• Thrive in environments where technical excellence drives business results and research breakthroughs.

Responsibilities

• Design, build, and maintain the distributed systems that serve Claude to millions of users worldwide.
• Develop resilient, flexible systems that adapt in real time to real world events.
• Develop intelligent request routing, load balancing, and traffic management systems across thousands of accelerators and multiple cloud providers.
• Maximize compute efficiency and optimize cost across the fleet by autoscaling and orchestrating production, research, and experimental workloads across multiple cloud providers.
• Build and operate production‑grade deployment pipelines for releasing new models to users.
• Provide high-performance inference infrastructure that enables researchers to develop next‑generation models.
• Integrate new AI accelerator platforms and support inference for new model architectures.

Skills

Distributed systems

Load balancing

Traffic management

Python

Rust

Kubernetes

AWS

GCP

Azure

Education

Bachelor’s degree or equivalent

Tools

Kubernetes

AWS

GCP

Azure

Job description

Anthropic Limited seeks an experienced Software Engineer to join the Inference team and scale Claude’s inference stack across multiple clouds and accelerators. You will design, deploy, and operate distributed, high‑performance systems; implement intelligent request routing, autoscaling, and production pipelines used by researchers and millions of users.

Compensation ranges from $320,000 to $485,000 USD per year.