Staff Software Engineer—Scalable AI Infra & Safe Execution

Anthropic Limited; San Francisco (CA); Hybrid; USD 320,000 - 485,000; Full time

Job summary

Anthropic is seeking a talented engineer to join the Claude App Infrastructure team. You will design and build sandboxed compute environments, implement long-running agent task management, and secure delegated access to support Claude's execution at scale.

You'll collaborate with product and research teams, build observability tools, and help ensure reliability as Claude evolves to act in the world, not just respond. This role blends security, performance, and scalable architecture.

Qualifications

• Experience building distributed systems, infrastructure, or platform services at scale.
• Comfort building cloud native infrastructure on GCP, AWS, or Azure
• Experience with containers, sandboxing, or secure execution environments (e.g., gVisor, Firecracker, V8 isolates)
• Write clean, maintainable code in Python, Go, Rust, or a similar language
• Care about security, isolation, and building systems that fail safely

Responsibilities

• Design and build sandboxed compute environments where Claude can safely execute code, access tools, and interact with external services
• Build state management systems for long-running agent tasks, handling checkpoints, recovery, and resumption across failures
• Develop authentication and authorization frameworks for delegated access, so Claude can act on behalf of users securely
• Create observability and debugging tools for agent execution, so we understand what Claude did, why, and how to make it better
• Partner closely with product and research teams to define what's possible and ship it

Skills

Distributed systems

Cloud native infra

Containers

Sandboxing

Python

Go

Rust

Security

Education

Bachelor’s degree

Tools

gVisor

Firecracker

V8 isolates

Job description

Anthropic is seeking a talented engineer to join the Claude App Infrastructure team. You will design and build sandboxed compute environments, implement long-running agent task management, and secure delegated access to support Claude's execution at scale.

You'll collaborate with product and research teams, build observability tools, and help ensure reliability as Claude evolves to act in the world, not just respond. This role blends security, performance, and scalable architecture.