Attiva gli avvisi di lavoro via e-mail!
A leading company is seeking an individual to help test and evaluate an AI agent. This role involves generating requests to provoke AI responses, classifying those responses, and working with a team in a fully remote environment. Full training is provided to prepare you for the tasks, and the position offers flexibility through a potential extension depending on project needs.
This project aims to test and evaluate an AI agent during its development stage. By asking questions and requests based on various categories (training provided), you will attempt to provoke the AI to produce harmful, offensive, dangerous, or toxic responses, which will then be evaluated.
The goal is to prevent the AI from sharing any harmful content with end users, thereby making it safer.
This role is fully remote, full-time, and lasts several months (potentially extended depending on project progress).
Full online training will be provided before starting the project.
Responsibilities:
Requirements:
J-18808-Ljbffr