Drimva

Anthropic

Staff+ Software Engineer, Claude Managed Agents

$405K–$485K

San Francisco, CA +2 · Staff · Full-time · Posted Aug 20, 2026

Location
San Francisco, CA
New York City, NY
San Francisco, California, United States
Experience
Minimum 8 years of practical experience; logistics state years required correlate with internal job-level requirements.
Education
Bachelor’s degree or an equivalent combination of education, training, and/or experience; required field of study is relevant to the role, demonstrated through coursework, training, or professional experience.
Visa sponsorship
Visa sponsorship is available, but not for every role or candidate; if an offer is made, Anthropic will make every reasonable effort to obtain a visa.

About the job

Build and operate Claude Managed Agents, a production platform for running scalable, long-lived AI agents, including its distributed systems, agent harness, evaluation capabilities, and developer-facing APIs.

What you'll do

  • Design and operate durable sessions, storage, sandbox orchestration, streaming, scheduling, and multi-tenant infrastructure.
  • Evolve the agent harness and build evaluation infrastructure to measure its performance against research baselines and customer workloads.
  • Develop agent capabilities and stable APIs, SDKs, and CLI interfaces in partnership with product, research, and other teams.

What they ask for

  • Minimum 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, with rigorous reasoning about durability, consistency, failure modes, and cost.
  • Strong product sense and API design skills; able to develop and execute product strategy with cross-functional partners.
  • Use Claude or other AI tools as a core part of software development; take ownership through deployment and operations, including on-call.

Nice to have

  • Experience building agent harnesses, frameworks, LLM orchestration, or LLM/agent evaluation infrastructure.
  • Experience with AI/ML platforms, durable execution or workflow engines, sandboxed execution, container runtimes, or public developer platforms and APIs.

Pay

$405,000 — $485,000 USD base salary

Tools

Claude, API, SDK, CLI

AI focus

Build and evaluate agent harnesses and production agent platform capabilities, including tool execution, context management, memory, multi-agent orchestration, and observability.

Model-written summary · the original posting is authoritative

First seen Oct 10, 2026 · Last verified Nov 5, 2026 (UTC)