🤔 What's the Project About?
This project focuses on testing and evaluating an AI agent that's still under development. Your role will be to ask the AI agent a variety of questions and requests, based on specific categories (we'll train you on those). The goal is to try and encourage the AI to produce content that's harmful, offensive, or dangerous in some way, and then evaluate the AI's responses.
Ultimately, we're aiming to prevent the AI from sharing any harmful or toxic content with end users, making it a safer tool for everyone.
📅 Project Details:
This is a fully remote, full-time contract role, designed to last for several months. Depending on how the project goes, it might be extended.
💻 Before you start, you'll get comprehensive online training.
What You'll Do:
- 🧑💻 Generate requests: Create questions and requests for the AI agent based on the topics we provide.
- 📝 Evaluate and classify: Review the AI's responses and categorize them.
- 🎯 Meet daily goals: We'll have specific targets for you to meet each day.
- 🤝 Communicate with your supervisor: Stay in touch with your supervisor to discuss your progress and any challenges you encounter.
What We're Looking For:
- 🇵🇹 Fluent Portuguese: This is a must-have for this role.
- 🇬🇧 Intermediate English: You'll need to understand English for training materials and communication within the team.
- 💻 Tech Savviness: Basic tech skills are important.
- ⏱️ Good Time Management: You'll need to manage your time efficiently to meet your daily goals.
- 🌟 Responsibility: This role requires a strong sense of responsibility.
- 🧠 Quick Learner: We're looking for someone who can quickly grasp new concepts and adapt to the project's needs.
Job Category: AI & Machine Learning