Full-Stack AI Product Engineer - LLM-Powered Interfaces

Anthropic Limited; San Francisco (CA); Hybrid; USD 300,000 - 320,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching

Generous vacation

Parental leave

Flexible working hours

Office space in SF

Job summary

Anthropic is seeking a Product Engineer to own end-to-end delivery of computer-use and browser-control product surfaces, building from UI to the agent runtime and backend services. You will work directly with researchers, with no layers between you and the model or user, in a role that rewards adaptability and prioritization of impact.

As a strong cross-functional contributor, you will ship external-user facing features, instrument usage data for prioritization, and collaborate with the Claude

Qualifications

• Experience building and shipping a product from zero to one with end-to-end ownership.
• Strong full-stack engineering skills, including production web frontend and backend.
• Hands-on experience with LLM APIs, prompting, or agent frameworks.
• Track record of shipping to external users and iterating based on feedback.

Responsibilities

• Own end-to-end delivery of computer-use and browser-control product surfaces: scope, build, ship, measure, and iterate.
• Diagnose and resolve reliability issues in the computer-use agent harness.
• Partner with computer-use researchers.
• Collaborate with Claude Cowork team on shared surfaces, integrations, and workflows.
• Instrument products and use data to drive prioritization and measure progress.
• Translate fuzzy user pain points into concrete features for knowledge workers.

Skills

Full-stack engineering

LLM APIs

Agent frameworks

External users shipping

Education

Bachelor's degree

Job description

Anthropic is seeking a Product Engineer to own end-to-end delivery of computer-use and browser-control product surfaces, building from UI to the agent runtime and backend services. You will work directly with researchers, with no layers between you and the model or user, in a role that rewards adaptability and prioritization of impact.

As a strong cross-functional contributor, you will ship external-user facing features, instrument usage data for prioritization, and collaborate with the Claude