Staff+ Software Engineer, Claude Managed Agents

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

We are looking for experienced backend and distributed systems engineers to join the Agentic Systems team within our Platform organization. Agentic Systems builds Claude Managed Agents: the hosted platform for building, running, and scaling production agents on Claude. Instead of every developer hand-rolling an agent loop, sandboxed execution, state management, credential handling, and error recovery — and reworking all of it with every model release — Managed Agents pairs an Anthropic-built agent harness with production infrastructure for sessions, environments, tools, memory, and permissions, exposed through a small set of composable APIs designed to stay stable as models and harnesses evolve. It powers agentic products inside Anthropic as well as those built by customers on the Claude Platform.

Managed Agents is in public beta and growing quickly, and this is still an early team with a lot of surface area left to define. You'll drive 0 → 1 efforts from ideation through GA, own systems end to end from API design through operations, and partner closely with product, research, developer experience, and go-to-market teams to figure out what "managed" should mean for the next generation of agents. You should be comfortable going deep on hard distributed systems problems, care about APIs as a product in their own right, and be motivated by turning ambiguous ideas into high-quality, shipped platform capabilities that other engineers build their products on.

Scale the platform. Managed Agents runs long-lived, stateful sessions that execute autonomously for minutes or hours/days, persist through disconnections, and resume cleanly — across Anthropic-hosted sandboxes, self-hosted environments on customer infrastructure, and other clouds. You'll design and operate the systems underneath that: durable session and event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation. Reliability, latency, and cost efficiency are product features here, and you'll own them in production.

Evolve the harness — and prove it with evals. The harness is the loop that calls Claude, routes tool calls, manages context (caching, compaction, memory), and recovers from errors. Harnesses encode assumptions about what the model can't yet do on its own, and those assumptions go stale as models improve. You'll work alongside research to revisit them with each model generation, build the eval infrastructure that measures harness quality against research baselines and real customer workloads, and hold the bar that lets us say our harness gets the most out of Claude.

Help builders get the most out of Claude. Our customers — internal and external — are building agents both as products for their users and to transform their own operations. You'll ship the capabilities that raise the ceiling on what those agents can do: outcome-driven execution where developers specify success criteria and a budget and Claude iterates until it gets there, multi-agent orchestration, memory, and the observability and tracing that make long-running agents debuggable. The goal is the highest intelligence per dollar of any agent platform, delivered safely.

Design APIs that outlast their implementations. Agents, environments, sessions, vaults, and event streams are interfaces thousands of developers build against and that our own products depend on. You'll shape