Anthropic3 days ago
Staff+ Software Engineer, Claude Managed Agents
Salary not specified
MARKET
15,900 ₽median for this role
Data Scientist · 115 jobs with disclosed pay
5,000half of the offers: 12,796–20,50043,793
The employer didn't disclose pay — compare with the market yourself.
San Francisco
Responsibilities
- 01Drive 0 → 1 efforts from ideation through GA, owning systems end‑to‑end from API design to operations and partnering with product, research, developer experience and go‑to‑market teams.
- 02Scale the platform by designing and operating durable session and event storage, sandbox orchestration, streaming, scheduling and multi‑tenant isolation, ensuring reliability, latency and cost efficiency.
- 03Evolve the agent harness, collaborate with research to revisit assumptions, build evaluation infrastructure measuring harness quality against baselines and customer workloads, and maintain high standards for harness performance.
- 04Ship capabilities that enable builders to get the most out of Claude, including outcome‑driven execution, multi‑agent orchestration, memory, observability and tracing for long‑running agents.
- 05Design stable, versioned APIs and SDKs for agents, environments, sessions, vaults and event streams, focusing on ergonomics, sensible defaults and escape hatches while implementations evolve.
Requirements
- 01Minimum of 8 years of practical experience as a backend, distributed systems, or infrastructure engineer.
- 02Built and operated stateful, long‑running, or high‑throughput systems in production (workflow orchestration, streaming, storage, container or job orchestration) and can reason rigorously about durability, consistency, failure modes and cost.
- 03Strong product sense; 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.
- 04Excited by 0 → 1 work, comfortable navigating ambiguity, and ideally have operated in both early‑stage and more mature team or company settings.
- 05Use Claude or other AI tools as a core part of how you build software and have opinions about what makes an agent harness good.
- 06Take full ownership of work from design through build, deployment and operations (including on‑call), and continuously iterate on and improve what you ship.
- 07Care about building systems that other engineers and businesses love to use, and about doing so safely.
- 08Built or contributed to an agent harness, agent framework, or LLM orchestration layer (tool execution, context management, memory, or multi‑agent coordination).
- 09Worked on an AI or ML platform (model serving, inference infrastructure, developer tooling) at an AI lab or AI‑native product company, or led adoption of AI‑driven development inside an engineering organization.
- 10Built evaluation or benchmarking infrastructure for LLM or agent systems.
- 11Experience with durable execution or workflow engines, sandboxed code execution, or container runtimes.
- 12Shipped public developer platforms, APIs, or SDKs used by external developers at scale.
What we offer
- 01Location preference: candidates based in NY, SEA, SF or the Bay Area.
- 02Deadline to apply: none; applications reviewed on a rolling basis.