Anthropic is building long-horizon visual RL environments to teach Claude knowledge work

An Anthropic Vision team role covers vendor-built tasks, reward design, held-out tests and fine-tuning Claude for specific agent tools and skills.

By · Published

A person stands facing glass doors in a concrete interior with shelves, chairs, plants, and “Rw” lettering.

An Anthropic Vision team role covers vendor-built tasks, reward design, held-out tests and fine-tuning Claude for specific agent tools and skills.