Staff+ Software Engineer, Claude Managed Agents

Details

Anthropic is seeking experienced backend and distributed systems engineers to join the Agentic Systems team within its Platform organization. The team builds Claude Managed Agents, a hosted platform for building, running, and scaling production agents on Claude. The platform provides an Anthropic-built agent harness with production infrastructure for sessions, environments, tools, memory, permissions, and composable APIs.

Managed Agents is in public beta and growing quickly. This early team offers significant ownership of 0-to-1 initiatives, from ideation through general availability, including API design, implementation, deployment, and operations.

Responsibilities

• Scale long-lived, stateful agent sessions that run autonomously for minutes, hours, or days, persist through disconnections, and resume cleanly.
• Design and operate durable session and event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation across Anthropic-hosted sandboxes, customer infrastructure, and other clouds.
• Own reliability, latency, and cost efficiency in production.
• Evolve the agent harness that calls Claude, routes tool calls, manages context through caching, compaction, and memory, and recovers from errors.
• Collaborate with research to revisit harness assumptions as models improve.
• Build evaluation infrastructure to measure harness quality against research baselines and real customer workloads.
• Ship capabilities including outcome-driven execution, multi-agent orchestration, memory, observability, and tracing for long-running agents.
• Design durable APIs for agents, environments, sessions, vaults, and event streams, including versioning, API/SDK/CLI ergonomics, sensible defaults, and escape hatches.
• Own work end to end from design through build, deployment, on-call operations, and iteration.
• Partner with product, research, developer experience, and go-to-market teams.

Requirements

• Minimum of 8 years of practical experience as a backend, distributed systems, or infrastructure engineer.
• Experience building and operating stateful, long-running, or high-throughput production systems, such as workflow orchestration, streaming, storage, container orchestration, or job orchestration.
• Ability to reason rigorously about durability, consistency, failure modes, and cost.
• Strong product sense and expertise in API design.
• Comfort with 0-to-1 work, ambiguity, and both early-stage and mature environments.
• Use of Claude or other AI tools as a core part of software development, with opinions about effective agent harnesses.
• Experience taking full ownership of systems from design through production operations.
• Bachelor's degree or an equivalent combination of education, training, and experience. The required field of study is a field relevant to the role, demonstrated through coursework, training, or professional experience.

Preferred Qualifications

• Experience building or contributing to an agent harness, agent framework, or LLM orchestration layer, including tool execution, context management, memory, or multi-agent coordination.
• Experience with AI or ML platforms, model serving, inference infrastructure, developer tooling, or AI-driven development adoption.
• Experience building evaluation or benchmarking infrastructure for LLM or agent systems.
• Experience with durable execution or workflow engines, sandboxed code execution, or container runtimes.
• Experience shipping public developer platforms, APIs, or SDKs used by external developers at scale.

Benefits

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and office space for collaboration. The current location-based hybrid policy expects staff to work from an office at least 25% of the time, although some roles may require more office time. Anthropic explicitly sponsors visas and will make every reasonable effort to obtain a visa for candidates receiving an offer, with support from an immigration lawyer.