This project aims to test and evaluate an AI agent during its development stage. Participants will ask questions and make requests across various categories (training will be provided) to challenge the AI to produce potentially harmful, offensive, dangerous, or toxic responses. The goal is to ensure the AI does not share such content with end users, thereby enhancing safety.This role is fully remote, full-time, and lasts several months, with the possibility of extension based on project progress.Participants will receive comprehensive online training before starting.Responsibilities:Generate requests to the AI agent on assigned topics;Evaluate and classify the AI's responses accordingly;Meet daily targets;Communicate with a supervisor.Requirements:Fluent in French;Intermediate English for training and team communication;Basic tech savviness;High responsibility level;Quick learner.
#J-18808-Ljbffr