AI Math Solution Evaluator

● JOB PROFILE
Evaluate AI-generated mathematics solutions for correctness, logical rigour, and proof validity. Rate responses across calculus, linear algebra, real analysis, differential equations, probability, and number theory. Produce structured, evidence-backed evaluation reports and quality-scored feedback for STEM AI model training datasets. This role is open to both coding and non-coding candidates — programming experience is valued but not mandatory.
● DESIRED CANDIDATE
Masters or higher (M.Sc / M.Tech / PhD) in Mathematics, Applied Mathematics, or Statistics — mandatory.
At least 1 published or peer-reviewed research paper in mathematics or a related field — mandatory.
Strong proof-writing, derivation, and mathematical reasoning skills.
Proficient in LaTeX for writing structured mathematical evaluations.
Coding / programming experience (Python, MATLAB, R, etc.) is a plus — non-coding candidates with strong domain expertise are equally welcome.
Ability to work independently and meet a minimum of 10 evaluated tasks per month.
Prior experience in AI/ML evaluation, annotation, or STEM tutoring is an advantage.