Staff Software Engineer: Scalable AI Inference Systems

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

Job summary

Anthropic is seeking to scale Claude’s AI inference infrastructure across cloud providers and accelerators. You will design and operate distributed systems, routing, and orchestration that serve millions of users worldwide.

The role requires deep experience with large-scale distributed systems, cloud platforms, and performance optimization, with a focus on reliable, interpretable AI infrastructure and researcher-friendly tooling. Hybrid office policy applies.

Qualifications

• Significant software engineering experience with distributed systems.
• Interest in learning ML systems and infrastructure.
• Willingness to work across multiple cloud providers and accelerators.

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

Skills

Distributed systems

Software engineering

Cloud infrastructure

Python or Rust

Load balancing

Routing & traffic management

Education

Bachelor’s degree

Tools

Kubernetes

AWS

GCP

Azure

Job description

Anthropic is seeking to scale Claude’s AI inference infrastructure across cloud providers and accelerators. You will design and operate distributed systems, routing, and orchestration that serve millions of users worldwide.

The role requires deep experience with large-scale distributed systems, cloud platforms, and performance optimization, with a focus on reliable, interpretable AI infrastructure and researcher-friendly tooling. Hybrid office policy applies.