Software Engineer, Agent SDK

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems, aiming for AI to be safe and beneficial for users and society. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders collaborating to build beneficial AI systems.

The Role: Software Engineer, Agent SDK

The Claude Agent SDK serves as the foundational layer empowering autonomous AI agents, providing developers with the tools, agent loop, and context management capabilities found in Claude Code, programmable in Python and TypeScript. It enables agents to perform functions like reading files, running commands, searching the web, and editing code right out of the box.

We are seeking a Software Engineer to take full ownership and lead the Agent SDK. This role demands high ownership and autonomy, where you will define the SDK's technical direction, establish strong opinions on API design and developer experience, and act as the crucial link between internal teams building next-generation experiences (such as Claude Desktop, Cowork, and IDE extensions) and external developers creating production agents on Claude.

You will need excellent judgment to prioritize development, balancing numerous requests from internal and external stakeholders with a clear product vision for what an outstanding agentic SDK should be.

Responsibilities

• Own the roadmap and technical direction for the Claude Agent SDK (Python and TypeScript).
• Design clean, intuitive APIs that facilitate the creation of powerful, reliable agents.
• Partner closely with internal teams building on Agent SDK – including Claude Desktop, Cowork, and IDE extensions – to understand their needs and prioritize development accordingly.
• Engage directly with external developers to comprehend their usage of the SDK, identify friction points, and uncover opportunities for next-generation use cases.
• Elevate the quality bar for documentation, examples, and the overall developer experience.
• Collaborate with other Claude Code engineers to expose new model capabilities through clean SDK abstractions.

You may be a good fit if you

• Have strong opinions about what great developer tools look like, grounded in experience building or using them.
• Are energized by owning something end-to-end, from API design through documentation to developer adoption.
• Have experience designing and shipping developer-facing SDKs or APIs, and understand the difference between a loved SDK and one merely tolerated.
• Are excited about the frontier of agentic AI – agents that can reason, plan, and act autonomously.
• Have hands-on experience with agentic patterns: tool use, orchestration, context management, multi-step reasoning.
• Can operate independently in ambiguous environments and drive projects forward without constant direction.
• Care about the societal implications of the technology you build.
• Have 5+ years of software engineering experience.

Strong candidates may also have

• Maintained a project built on the Claude Agent SDK.
• Experience managing an open source project on GitHub – triaging issues, prioritizing tasks, and engaging with community contributors.
• Experience scaling TypeScript or Python library codebases.
• Shipped SDKs or APIs used by external developers in production.
• Opinions about API versioning, backwards compatibility, and managing ecosystem migrations.

Compensation

The annual compensation range for this role is $320,000—$485,000 USD.

Logistics & Culture

Education requirements include at least a Bachelor's degree in a related field or equivalent experience. Anthropic operates under a location-based hybrid policy, requiring staff to be in one of our offices at least 25% of the time, though some roles may require more. Visa sponsorship is available, and Anthropic makes every reasonable effort to secure visas for successful candidates. We encourage all interested individuals, including those from underrepresented groups, to apply even if they don't meet every qualification, as diverse perspectives are crucial for building ethical AI systems. Anthropic is a public benefit corporation based in San Francisco, offering competitive compensation, benefits, and a collaborative environment focused on high-impact AI research, as outlined in our published research directions.

Key skills/competency

• Agent SDK
• API Design
• Developer Experience
• Python
• TypeScript
• Autonomous AI Agents
• Tool Use
• Orchestration
• Context Management
• System Design