About the role
The Computer Use team teaches Claude to see and operate computer interfaces, and builds the agent harness and end-user products that turn that capability into real tools. The team sits inside Anthropic's research organization and closes the loop between product and model.
As a Product Engineer on this team, you'll own end-to-end delivery of our computer-use and browser-control product surfaces. You'll build across the full stack, from the user interface to the agent runtime to the backend services behind it. You'll work directly alongside researchers, with no layers between you and the model or the user.
This is a dynamic role in which priorities evolve frequently. Success depends on a high tolerance for ambiguity, the adaptability to shift focus as needs change, and the agility and discernment to continuously prioritize the highest impact work.
Key responsibilities
-
Own end-to-end delivery of computer-use and browser-control product surfaces: scope, build, ship, measure, and iterate
-
Diagnose and resolve reliability and robustness issues in the computer-use agent harness that block real-world usage
-
Partner with computer-use researchers
-
Partner with the Claude Cowork team on shared surfaces, integrations, and knowledge-worker workflows
-
Instrument products and use usage data to drive prioritization and measure progress
-
Translate fuzzy user pain points into concrete, shippable features for knowledge workers
Minimum qualifications
-
Experience building and shipping a product from zero to one with end-to-end ownership, as a founding or early engineer at a startup or with equivalent ownership inside a larger company
-
Strong full-stack engineering skills, including production web frontend and backend development
-
Hands-on experience building with LLM APIs, prompting, or agent frameworks
-
A track record of shipping to external users and iterating based on their feedback
Preferred qualifications
-
Strong product design instincts and the ability to produce a clean, usable interface without a dedicated designer
-
Experience with browser automation, desktop automation, or robotic process automation systems
-
Experience building evals or quality harnesses for machine learning systems
-
Comfort with lightweight data analysis, such as SQL, notebooks, and defining and tracking product metrics
-
Experience designing agent loops, tool integrations, or guardrails for LLM-based systems
Representative projects
-
Own and resolve the top reliability and robustness issues on the computer-control and browser-control product surfaces, with measurable improvement in task success rate
-
Take a net-new computer-use powered workflow from concept to external users, including instrumentation and a readout on usage
