STEM PhD Evaluator (Mathematics)

Vettedlance; United States; Remote; USD 83,000 - 124,000; Part time

Job summary

Vettedlance is seeking PhD mathematicians to craft graduate-level problems and provide rigorous, step-by-step grading of model proofs. You will identify where a model's reasoning fails and explain why, as well as review other experts' items for quality and difficulty.

The role is remote and hourly, part-time with 10–40 hours per week. Strong English writing and LaTeX fluency are required to produce clear, publishable materials for AI evaluation.

Qualifications

• Fluent written English.
• Comfortable writing in LaTeX.

Responsibilities

• Write original graduate-level problems with verified solutions.
• Grade model proofs and derivations step by step against a rubric.
• Identify the exact step where a model's reasoning fails and explain why.
• Review other experts' items for correctness and difficulty.

Skills

LaTeX

Education

PhD in mathematics or applied mathematics

Job description

PhD mathematicians write and grade graduate-level problems and step-by-step proofs used to train and evaluate AI models.

What you will do

• Write original, graduate-level problems with verified solutions
• Grade model proofs and derivations step by step against a rubric
• Identify the exact step where a model's reasoning fails and explain why
• Review other experts' items for correctness and difficulty

What you need

• PhD in mathematics or applied mathematics, completed
• Publications, a faculty post or equivalent research record
• Fluent written English
• Comfortable writing in LaTeX

Contract

• Remote, hourly contract (independent contractor)
• Part-time, flexible: 10-40 hrs/week
• Remote

Pay: $60 - $90 / hour (USD). Paid in USD, weekly. Rate set after a short paid assessment.