Staff+ Software Engineer, Claude Managed Agents en Anthropic

Presencial - San Francisco, CA; New York City, NY

Postularse
Más vacantes en Anthropic

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 – a hosted platform for building, running, and scaling production agents on Claude. The role involves driving 0→1 efforts from ideation through GA, owning systems end to end from API design through operations, and partnering closely with product, research, developer experience, and go‑to‑market teams to define the next generation of managed agents. Candidates will design and operate large‑scale, stateful session infrastructure, evolve the agent harness, ship capabilities that help builders get the most out of Claude, and design robust, version‑stable APIs for developers and internal products. This is a full‑time, onsite position based in San Francisco, CA or New York City, NY, with competitive compensation, benefits, and a collaborative, research‑driven culture at Anthropic.

Requirements

Skills

  • Minimum of 8 years of practical experience as a backend, distributed systems, or infrastructure engineer
  • Built and operated stateful, long-running, high-throughput systems in production – workflow orchestration, streaming, storage, container or job orchestration – and can reason rigorously about durability, consistency, failure modes, and cost
  • Strong product sense and treat API design as a craft; care about the developer on the other side of the interface and can ideate and execute product strategy with cross‑functional partners
  • Excited by 0→1 work and comfortable navigating ambiguity, with ideally operated in both early‑stage and more mature team or company settings
  • Uses Claude or other AI tools as a core part of how they build software, with opinions about what makes an agent harness good
  • Takes full ownership of their work – from design through build, deployment, and operations (including on‑call) – to iterating on and improving what they ship
  • Cares about building systems that other engineers and businesses love to use, and about doing so safely

Responsibilities

  • Scale the platform by designing and operating durable session and event storage, sandbox orchestration, streaming, scheduling, and multi‑tenant isolation
  • Evolve the harness, build eval infrastructure to measure harness quality, and revise it with each model generation
  • Help builders get the most out of Claude by shipping outcome‑driven execution, multi‑agent orchestration, memory, and observability and tracing features
  • Design APIs that outlast their implementations, shaping primitives, versioning, ergonomics, defaults, and escape hatches

Technologies

Backend engineeringDistributed systemsInfrastructureAPI designSandbox orchestrationStreamingSchedulingMulti‑tenant isolationEvaluation infrastructureLLM harnessClaudeWorkflow enginesSandboxed code executionContainer runtimesPublic developer platformsAPIsSDKs

Compartir vacante

Descubre si tu currículum está listo para esta vacante

Mira cómo nuestra IA puede optimizar tu currículum y aumentar tus chances en este puesto.