SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Anthropic is hiring a Staff Software Engineer to join the Claude App Infrastructure team, responsible for the reliability, experience, and agentic capabilities of claude.ai. This is a platform engineering role at the heart of Anthropic's flagship consumer product.
You'll own the serving architecture that keeps Claude available at scale, the conversation experience, and the infrastructure that enables all product teams to ship safely and quickly. As the product grows at hyper scale, your team ensures the experience remains seamless or improves.
Key focus areas include building the agentic layer that transforms claude.ai from a chat interface into an execution platform. You'll design and build sandboxed compute environments where Claude can safely execute code, access tools, and interact with external services. You'll create state management systems for long-running agent tasks, handling checkpoints, recovery, and resumption across failures. You'll develop authentication and authorization frameworks for delegated access, enabling Claude to act on behalf of users securely.
Additionally, you'll create observability and debugging tools for agent execution, ensuring visibility into what Claude does and why. You'll partner closely with product and research teams to define what's possible and ship it.
Required experience includes building distributed systems, infrastructure, or platform services at scale; comfort with cloud-native infrastructure on GCP, AWS, or Azure; experience with containers, sandboxing, or secure execution environments (gVisor, Firecracker, V8 isolates); ability to write clean, maintainable code in Python, Go, Rust, or similar languages; and a focus on security, isolation, and systems that fail safely.
Preferred qualifications include comfort with ambiguity and greenfield work where you help shape architecture, and interest in novel problems without existing playbooks.
