Staff+ Software Engineer, Claude App Infrastructure
$181k - $198k • San Francisco, CA | New York City, NY | Seattle, WA
Posted 16d ago
About the job
Claude App Infrastructure owns the reliability, experience, and agentic capabilities of claude.ai. We are 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 allows product teams to ship into claude.ai safely and quickly. We are building the agentic layer that transforms claude.ai from a chat surface into an execution surface, enabling task execution, personalization, browser use, and server-side tools. Our goal is to build systems that ensure both reliability and velocity.
Responsibilities
- Design and build sandboxed compute environments for safe code execution, tool access, and external service interaction.
- Build state management systems for long-running agent tasks, including checkpointing, recovery, and resumption across failures.
- Develop authentication and authorization frameworks for secure delegated access.
- Create observability and debugging tools for agent execution to understand behavior and identify improvements.
- Collaborate closely with product and research teams to define and implement new capabilities.
Requirements
- Experience building distributed systems, infrastructure, or platform services at scale.
- Proficiency in building cloud-native infrastructure on GCP, AWS, or Azure.
- Experience with containers, sandboxing, or secure execution environments (e.g., gVisor, Firecracker, V8 isolates).
- Ability to write clean, maintainable code in Python, Go, Rust, or a similar language.
- A strong focus on security, isolation, and building systems that fail safely.
- Comfort with ambiguity and greenfield work, shaping architecture.
- 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.