Who are we? Cohere is the leading security-first enterprise AI company. We build cutting-edge foundation AI models and end-to-end products that are designed to solve real-world business problems.
Project Meteor | AI Response & Rubric Evaluation
Job description
Description:
OneForma is looking for detail-oriented contributors to join Project Meteor, a remote AI evaluation project.
Participants will review and improve AI-generated golden responses and evaluation rubrics to ensure they meet the highest quality standards and are free of critical (P0) errors. The work includes evaluating AI outputs for both open-ended and close-ended tasks using detailed project guidelines.
This is a flexible remote opportunity for individuals who enjoy analytical work and have strong reading comprehension and attention to detail.
Purpose:
The purpose of this project is to improve the quality of AI-generated responses by refining reference answers and evaluation rubrics used to train and assess advanced multilingual AI models.
Main Responsibilities:
- Review AI “golden responses” for quality and accuracy.
- Evaluate and improve AI evaluation rubrics.
- Identify and correct critical (P0) issues.
- Follow detailed annotation guidelines.
- Deliver high-quality work while meeting project requirements.
Requirements:
- Native-level fluency in one of the project languages.
- Strong written communication skills.
- Excellent attention to detail.
- Basic familiarity with medical, financial, and legal topics.
- Reliable internet connection.
- Ability to carefully follow project instructions.
Apply today and help improve the next generation of multilingual AI systems.
You will be redirected to the company's website to complete your application.