Join the Appen team as an Independent Contractor for Project Aralia, contributing to the advancement of AI technology. In this 6-8 week project, you will play a crucial role in evaluating model responses to various commands, aiding in the refinement and improvement of AI algorithms.

Responsibilities:

Read a prompt and evaluate two model responses to each. Use the criteria provided to judge each answer based on three things: whether it's harmless, honest, and helpful. Rate responses based on predetermined criteria by answering several questions. Compare the answers to see which one is better overall and by how much. Maintain a high level of accuracy and consistency in evaluations.

Key Details:

• Each unit (command and model responses) takes approximately 5 minutes to evaluate.

• Contractors have the flexibility to work on an unlimited number of units.

• Compensation is based on the hours spent actively working in the evaluation tool.

We're seeking individuals with a strong work ethic, commitment to quality, and attention to detail. Ideally, you can commit to 25 hours per week over a 6-8 week period. Enjoy the benefits of remote and independent work, offering schedule flexibility.

Apply to the project today, access available resources to guide, educate, and test your task proficiency.

Join us in shaping the future of AI technology. Apply now to become a vital part of the Aralia project!

Requirements:

• Fluent/native speaker of English.

• Residing in the United States.

• Age 18 or above.

• Access to a laptop or PC.

Qualifications:

• Sign relevant project contracts and/ or agreements.

• Complete a short 5-minute survey.

• Complete a Guidelines Quiz (approx. 15mins) to ensure you understand LLM based modelling.

• Complete a Task Test (approx. 30 minutes) to ensure you understand the project and the work that will need to be done.

• Complete an identity check to validate your identity.