Staff+ Software Engineer, Claude Managed Agents
Build and operate Claude Managed Agents, a production platform for long-running autonomous agents. The role requires 8+ years of backend, distributed systems, or infrastructure experience, strong API and product judgment, and expertise in reliable, stateful systems.
About the job
Responsibilities
- Scale Claude Managed Agents, including durable session and event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation.
- Design and operate long-lived, stateful agent sessions across Anthropic-hosted sandboxes, customer infrastructure, and other clouds.
- Evolve the agent harness for tool calls, context management, memory, error recovery, and model-generation changes.
- Build evaluation infrastructure to measure harness quality against research baselines and customer workloads.
- Ship capabilities such as outcome-driven execution, multi-agent orchestration, memory, observability, and tracing.
- Design durable APIs for agents, environments, sessions, vaults, and event streams, including versioning, SDK, and CLI ergonomics.
- Own systems end to end from design through deployment, operations, on-call, and iteration.
- Partner with product, research, developer experience, and go-to-market teams on new platform capabilities.
Requirements
- Minimum 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.
- Strong understanding of durability, consistency, failure modes, reliability, latency, and cost efficiency.
- Strong product sense and API design skills.
- Comfort with 0-to-1 work, ambiguity, cross-functional collaboration, and full ownership.
- Experience using Claude or other AI tools as part of software development.
- Commitment to safe, high-quality systems used by other engineers and businesses.
- Bachelor’s degree or equivalent combination of education, training, and experience in a relevant field.
Nice-to-haves
- Experience building agent harnesses, agent frameworks, or LLM orchestration layers.
- Experience with tool execution, context management, memory, or multi-agent coordination.
- Experience with AI or ML platforms, model serving, inference infrastructure, or AI-driven development.
- Experience building evaluation or benchmarking infrastructure for LLM or agent systems.
- Experience with durable execution, workflow engines, sandboxed code execution, or container runtimes.
- Experience shipping public developer platforms, APIs, or SDKs used by external developers at scale.
Compensation and Benefits
- Annual salary range: $405,000–$485,000 USD.
- Hybrid policy: staff are currently expected to work from an office at least 25% of the time.
- Visa sponsorship is available for eligible roles and candidates.
Skills
Distributed Systems, Backend Engineering, Infrastructure, API Design, Claude, Llm Orchestration, Agent Harnesses, Event Streaming, Storage Systems, Sandbox Orchestration, Container Runtimes, Multi-Tenant Isolation, Observability, Tracing, Workflow Engines
Similar jobs
Backend Engineering jobs
Anthropic
San Francisco, CAOwn and shape highly available authentication, authorization, and identity infrastructure for Anthropic’s products, including agent and enterprise identity capabilities. The role requires 8+ years building backend or platform systems at scale, strong security and reliability practices, and experience with identity protocols or distributed systems.
Anthropic
San Francisco, CABuild and scale Anthropic’s cloud-native Claude Platform across AWS, Google Cloud, and Azure, while delivering enterprise security, compliance, and data-residency capabilities. The role requires 8+ years of backend or platform engineering experience, distributed-systems expertise, and proficiency in Python, Go, Rust, or similar languages.
Anthropic
San Francisco, CABuild and operate Anthropic’s connectivity platform, including MCP proxy infrastructure, OAuth and token management, enterprise controls, and reliability systems. The role requires strong backend or platform engineering experience, distributed-systems expertise, and the ability to lead complex architectural work across teams.
Anthropic
San Francisco, CAStaff-level software engineer building secure, scalable execution infrastructure for Claude’s agentic capabilities. The role requires 8+ years of backend or platform engineering experience, strong distributed-systems and systems-design fundamentals, and proficiency in systems languages and cloud infrastructure.
Anthropic
San Francisco, CA
Design and operate high-QPS backend systems on Claude’s token-generation path, owning latency, reliability, safe deployments, and incident response. The role requires 8+ years of software engineering experience, strong distributed-systems expertise, and production ownership of mission-critical services.