Staff+ Software Engineer (Claude Managed Agents)

Location: San Francisco, CA or New York City, NY; hybrid attendance in an Anthropic office at least 25% of the time. Preference is given to candidates based in NY, Seattle, San Francisco, or the Bay Area.

Annual salary: $405,000–$485,000 USD

Company

Anthropic builds reliable, interpretable, and steerable AI systems and develops Claude and related platform technologies.

What you will do

• Scale Claude Managed Agents across long-lived stateful sessions, hosted sandboxes, customer infrastructure, and multiple clouds.
• Design and operate durable session and event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation.
• Evolve the agent harness for tool execution, context management, memory, error recovery, and changing Claude model capabilities.
• Build evaluation infrastructure for agent harness quality using research baselines and customer workloads.
• Deliver platform capabilities including outcome-driven execution, multi-agent orchestration, memory, observability, and tracing.
• Shape stable APIs, SDKs, and CLI interfaces for agents, environments, sessions, vaults, and event streams.

Requirements

• At least 8 years of practical experience as a backend, distributed systems, or infrastructure engineer.
• Production experience building and operating stateful, long-running, or high-throughput systems such as workflow orchestration, streaming, storage, or container orchestration.
• Strong understanding of durability, consistency, failure modes, reliability, latency, and cost efficiency.
• Strong product sense, API design skills, ownership from design through deployment and operations, and comfort with ambiguity and 0→1 work.
• Bachelor’s degree or equivalent combination of education, training, and experience.
• Visa sponsorship is available, subject to role and candidate eligibility.

Nice to have

• Experience building agent harnesses, agent frameworks, LLM orchestration layers, or AI/ML platforms.
• Experience with LLM evaluation, benchmarking, durable execution, workflow engines, sandboxed code execution, or container runtimes.
• Experience shipping public developer platforms, APIs, or SDKs used by external developers at scale.

Culture & Benefits

• Collaborative, research-driven environment focused on safe and beneficial AI.
• Flexible working hours and office collaboration.
• Competitive compensation, optional equity donation matching, generous vacation, and parental leave.
• Support from an immigration lawyer for sponsored visa applications.