Staff+ Software Engineer, Claude Managed Agents
Remote • San Francisco, CA | New York City, NY
Posted 2d ago
About the job
Anthropic is seeking experienced backend and distributed systems engineers to join the Agentic Systems team. This team builds Claude Managed Agents, a hosted platform for creating, running, and scaling production agents on Claude. The platform provides essential functionalities like agent loops, sandboxed execution, state management, credential handling, and error recovery, exposed through stable APIs. This role involves driving new features from ideation to general availability, owning systems end-to-end, and collaborating with product, research, developer experience, and go-to-market teams. The ideal candidate will be comfortable tackling complex distributed systems challenges, have a strong product sense for API design, and be motivated by transforming ambiguous ideas into high-quality platform capabilities.
Responsibilities
- Design and operate systems for durable session and event storage, sandbox orchestration, streaming, scheduling, and multi-tenant isolation to scale the platform.
- Own reliability, latency, and cost efficiency as product features for the platform.
- Work with research to evolve the agent harness, building evaluation infrastructure to measure harness quality.
- Ship capabilities that enhance agent functionality, such as outcome-driven execution, multi-agent orchestration, memory, and observability/tracing.
- Design and maintain stable APIs for agents, environments, sessions, vaults, and event streams, considering versioning, ergonomics, and sensible defaults.
- Take full ownership of work, from design and build through deployment, operations, and iteration.
Requirements
- Minimum of 8 years of practical experience as a backend, distributed systems, or infrastructure engineer.
- Experience building and operating stateful, long-running, or high-throughput systems in production (e.g., workflow orchestration, streaming, storage, container/job orchestration).
- Ability to reason rigorously about durability, consistency, failure modes, and cost.
- Strong product sense and a craft-oriented approach to API design, with consideration for the developer experience.
- Ability to ideate and execute product strategy with cross-functional partners in new domains.
- Comfort navigating ambiguity and performing 0 -> 1 work, with experience in both early-stage and mature team/company settings.
- Experience using Claude or other AI tools as a core part of software development.
- Experience building or contributing to an agent harness, agent framework, or LLM orchestration layer.
- Experience working on an AI or ML platform (model serving, inference infrastructure, developer tooling) or leading AI-driven development adoption.
- Experience building evaluation or benchmarking infrastructure for LLMs.