AI Agent Evaluator - Remote

Overview

This project aims to test and evaluate one AI agent in the development stage. By asking questions and requests, based on various categories (the training is provided), you will try to force the AI agent to say something harmful, offensive, dangerous or toxic and evaluate its responses.

In Short

• Test and evaluate an AI agent in development.
• Ask questions to provoke harmful responses.
• Evaluate AI responses for safety and toxicity.
• Prevent AI from sharing harmful content.
• Fully remote position.
• Full-time role for several months.
• Training provided before the project starts.
• Work on improving AI safety.
• Collaborate with a team of evaluators.
• Contribute to AI development and safety measures.

Requirements

• Interest in AI and technology.
• Ability to ask probing questions.
• Attention to detail in evaluating responses.
• Strong communication skills.
• Willingness to participate in training.
• Ability to work independently.
• Commitment to project duration.
• Experience with AI is a plus.
• Critical thinking skills.
• Open-mindedness towards AI development.

Benefits

• Flexible working hours.
• Gain experience in AI evaluation.
• Work remotely from anywhere.
• Opportunity to contribute to AI safety.
• Collaborate with experts in the field.
• Full training provided.
• Potential for project extension.
• Engage in meaningful work.
• Build skills in technology and evaluation.
• Be part of an innovative project.