Staff+ Software Engineer, Claude App Infrastructure

About the role

Claude App Infrastructure owns the reliability, experience, and agentic capabilities of claude.ai. We're the platform team for Anthropic's flagship consumer product, responsible for the serving architecture that keeps Claude available at scale, the conversation experience, and the infrastructure that lets every product team at Anthropic ship into claude.ai safely and fast. When the product grows at hyper scale, we're the team that makes sure it feels the same or better.

Beyond the foundation, we're building the agentic layer that turns claude.ai from a chat surface into an execution surface: task execution, personalization, browser use, and server-side tools. This is where the next generation of the product gets built: the primitives that let Claude act in the world, not just respond. We believe reliability and velocity are the same problem, and our job is to build the systems that make both inevitable.

Key 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

Minimum 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

Preferred qualifications

• Comfort with ambiguity and greenfield work where you help shape the architecture
• Interest in problems that don't have existing playbooks
• Experience building multi-tenant execution platforms or serverless infrastructure
• Background in security engineering, sandboxing, or isolation technologies
• Familiarity with workflow orchestration systems (Temporal, Airflow, Step Functions)
• Experience with state machines, checkpointing, or durable execution patterns
• Low-level systems experience (Linux internals, eBPF, container runtimes)