Staff+ Software Engineer, Claude Managed Agents

Anthropic
San Francisco, New York
Workplace: HybridFull timeUSD 405,000 - 485,000 annuallyFunction: Software EngineeringExperience: 8+ yearsEducation: bachelorsSkills: ["Product sense","API design","Ownership","Cross-functional collaboration","Navigating ambiguity"]

Build and operate the Claude Managed Agents platform, a hosted system for creating, running, and scaling production agents. You’ll design durable session and event storage, sandbox orchestration, streaming and scheduling, multi-tenant isolation, and reliability/latency/cost improvements. Partner with research and cross-functional teams to evolve the agent harness, develop eval infrastructure, and ship durable, composable APIs that keep working as models and implementations change.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Anthropic
Anthropic
1 day ago

Staff+ Software Engineer, Claude Managed Agents

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Build and operate the Claude Managed Agents platform, a hosted system for creating, running, and scaling production agents. You’ll design durable session and event storage, sandbox orchestration, streaming and scheduling, multi-tenant isolation, and reliability/latency/cost improvements. Partner with research and cross-functional teams to evolve the agent harness, develop eval infrastructure, and ship durable, composable APIs that keep working as models and implementations change.
Location: San Francisco, New York
Workplace: Hybrid
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Scale Managed Agents by designing and operating durable session/event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation.
  • •Own reliability, latency, and cost efficiency for long-lived, stateful agent sessions that persist and resume cleanly.
  • •Evolve the agent harness with research by revisiting assumptions, building eval infrastructure, and validating harness quality against baselines and workloads.
  • •Ship capabilities that increase what agents can do, including outcome-driven execution, multi-agent orchestration, memory, and observability/tracing.
  • •Design composable, stable APIs (and related primitives) so implementations can change while contracts remain reliable across SDK/CLI/API interfaces.

Pay and Benefits

Salary: USD 405,000 - 485,000 annually
Perks:Parental LeavePaid Leave

Key Requirements

  • •Minimum 8 years of practical experience as a backend, distributed systems, or infrastructure engineer.
  • •Built and operated stateful, long-running, or high-throughput production systems (e.g., orchestration, streaming, storage, container/job orchestration).
  • •Rigorously reason about durability, consistency, failure modes, and cost.
  • •Treat API design as a craft and use product sense to shape cross-functional product strategy.
  • •Take full ownership from design through build, deployment, and operations (including on-call).
Experience:8+ yearsDistributed systemsInfrastructureAgent platformsLLM orchestrationDeveloper platforms
Education:Bachelor's
Skills:Product senseAPI designOwnershipCross-functional collaborationNavigating ambiguity
Languages:English

Company Brief

Anthropic
Develops large-scale AI systems and safety research to create reliable, steerable, and interpretable AI assistants and models for commercial and research applications.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series C
Headquarters: San Francisco, United States
Founded: 2021
WebsiteLinkedIn