PhD Mathematics (Reasoning Evaluator for AI Systems)

To Apply

Please fill out the application form here: https://forms.gle/geqnx3i2Kdvu7ak47

About the Role

PhD-level Mathematics or Statistics experts

You’ll review and evaluate AI-generated mathematical responses, assess reasoning quality, and provide expert feedback to help improve model accuracy and logical clarity. This includes fact-checking quantitative information, identifying errors in methodology, and writing high-quality explanations that demonstrate correct mathematical thinking.

Key Responsibilities

• Review AI-generated mathematical solutions and reasoning steps

• Evaluate responses for accuracy, clarity, and adherence to prompts

• Identify conceptual or computational errors and provide corrective insights

• Develop and refine model solutions and explanations

• Rate and compare multiple responses based on reasoning quality

Required Qualifications

• PhD in Mathematics, Statistics, or a closely related quantitative field

• Experience developing or reviewing advanced math content (proofs, textbooks, research papers, etc.)

• Published in a peer-reviewed journal

• Excellent English proficiency (C1 or above) and analytical writing skills

Preferred Qualifications

• Experience in data labeling, RLHF, or AI model evaluation

Commitment

• Minimum 17–20 hours per week (preferred 8 hours/day)

• Remote, freelance engagement with flexible schedule

Compensation

Competitive and based on education level, institution, and experience.