Staff Software Engineer, Internal Products

Anthropic•San Francisco, NY

19h•Hybrid

About The Position

Anthropic is hiring a Staff+ full-stack engineer to build internal software that supports the work of teams across the company. The role focuses on Claude-first products that enable Claude to handle repetitive, multi-step work safely while people make decisions that require human judgment. The engineer will build both user-facing products and agents, work directly with the teams who use them, and ensure workflows that write to business-critical data are correct and reliable. This is a greenfield opportunity to shape underlying systems, deploy agents that reduce manual work, and design how people and agents access the context needed to make good decisions. The role includes setting technical direction over multiple quarters, leading engineers across teams through ambiguous projects, mentoring colleagues, and operating the systems delivered, including participating in on-call support. The position is hybrid under Anthropic’s current policy: staff are expected to work from an office at least 25% of the time, though some roles may require more. A bachelor’s degree or equivalent combination of education, training, and/or experience is required; the field of study must be relevant to the role as demonstrated through coursework, training, or professional experience. Required years of experience correlate with the internal job level. The annual salary range is $405,000–$485,000 USD.

Requirements

Experience shipping production software as a backend-leaning full-stack engineer, including designing data models, APIs, and user interfaces.
Experience building software on LLMs or agents, with a point of view on when an agent should act autonomously and when it should ask for confirmation.
Experience leading the design and delivery of complex, user-facing products across the full stack, including when requirements change during development.
Experience designing for correctness and data integrity from the start in systems where errors are costly and difficult to undo.
Experience working closely with non-engineering partners to turn ambiguous needs into clear requirements and reach decisions together.
Bachelor’s degree or an equivalent combination of education, training, and/or experience; a relevant field of study demonstrated through coursework, training, or professional experience.

Nice To Haves

Experience building internal tools or platforms relied on by other teams; this is a plus, and strong product generalists are also welcome.
Experience taking an agent into production for a high-stakes workflow, including the evaluations and guardrails used to make it safe to ship.
Experience building a zero-to-one product or rebuilding a product that people already depended on every day.
Experience building on third-party platforms through their APIs and knowing when to extend an existing system versus building a new one.

Responsibilities

Design and ship internal products end to end, from data models through APIs and user interfaces, for workflows used by teams across Anthropic.
Apply Claude to practical tasks such as gathering decision context, drafting steps in multi-step processes, and keeping records consistent across systems; determine when an agent should act and when a user interface is more appropriate.
Make agents safe for real work through scoped data access, guardrails, evaluations, audit trails, and clear human-confirmation points.
Build shared capabilities for people and agents, exposed through APIs and MCP tools, so the same rules and approvals apply to both.
Treat speed and product polish as requirements; work with users to identify slowdowns and remove unnecessary steps.
Design workflows for correctness, using idempotency, reconciliation, and audit trails where appropriate for business-critical data.
Integrate with third-party systems and build the layer where people and agents perform their work.
Set technical direction for a product area over multiple quarters and lead engineers across teams on large, ambiguous projects.
Improve the engineers around you through design reviews, code reviews, and mentorship.
Operate shipped workflows, own their reliability, and participate in on-call support.