Mathematics Domain Expert — AI Evaluation (Remote, US)

AuraOne Human Data; United States; Remote; USD 124,000 - 193,000; Full time

Job summary

AuraOne Human Data is seeking a Mathematics Domain Expert for AI Evaluation. This remote contractor role focuses on evaluating AI outputs, reproducing key derivations, and documenting correct methods to guide model training. The work requires strong math background and experience with scholarly sources.

Applicants should have graduate-level math training, publishing or teaching experience, and the ability to work asynchronously at least 10 hours per week from a US-based location.

Qualifications

• Graduate-level training or equivalent applied experience in mathematics or a closely related field.
• Hands-on experience publishing, teaching, or advising on the topic at a professional level.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that cites methods, papers, or worked examples.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Review AI outputs against current mathematics methods, conventions, and prior work for Mathematics Domain Expert — AI Evaluation (Remote, US) assignments.
• Reproduce or sanity-check key derivations, calculations, or experimental claims.
• Flag dimensional, methodological, and citation errors with structured severity tags.
• Capture the corrected reasoning or worked example so the modeling team can train on it.
• Adjudicate disputed answers against textbooks, papers, or community standards.
• Maintain reviewer-quality scores in inter-rater calibration cycles.

Skills

Scientific reasoning

Method validation

Citation review

Quantitative analysis

Mathematics

Education

Graduate-level training in mathematics

Job description

Mathematics Domain Expert — AI Evaluation (Remote, US) is a remote review track for evaluating AI outputs across mathematics reasoning, calculations, and research workflows. Reviewers grade derivations and assumptions, reproduce key results, and document the correct method so the modeling team can train on it.

Why this role matters

Mathematics models live or die on whether their derivations actually hold up under scrutiny. AuraOne uses scientific specialists to grade outputs the way a peer reviewer would — checking assumptions, reproducing key steps, and capturing the right method alongside the wrong one.

Responsibilities

• Review AI outputs against current mathematics methods, conventions, and prior work for Mathematics Domain Expert — AI Evaluation (Remote, US) assignments.
• Reproduce or sanity-check key derivations, calculations, or experimental claims.
• Flag dimensional, methodological, and citation errors with structured severity tags.
• Capture the corrected reasoning or worked example so the modeling team can train on it.
• Adjudicate disputed answers against textbooks, papers, or community standards.
• Maintain reviewer-quality scores in inter-rater calibration cycles.

Qualifications

• Graduate-level training or equivalent applied experience in mathematics or a closely related field for Mathematics Domain Expert — AI Evaluation (Remote, US) work.
• Hands-on experience publishing, teaching, or advising on the topic at a professional level.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that cites methods, papers, or worked examples.
• Reliable async availability for at least 10 hours per week.

Example tasks

• Reproduce a mathematics derivation from a model output and flag any algebraic or dimensional errors.
• Grade a model's literature summary against the cited papers and rate the citation quality.
• Adjudicate a disputed answer between two reviewers using textbook methods.
• Audit a 25-row batch for rubric consistency and report drift to the program lead.

Nice to have

• PhD, postdoc, or industry research experience in the topic area.
• Prior work reviewing AI-assisted research tooling and its failure modes.
• Multilingual fluency for non-English papers and corpora.

Skills

• Scientific reasoning
• Method validation
• Citation review
• Quantitative analysis
• Mathematics

Work model

Remote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

Compensation

$90–$140 / hr

Graduate-level training or equivalent applied experience in mathematics or a closely related field for Mathematics Domain Expert — AI Evaluation (Remote, US) work. Hands-on experience publishing, teaching, or advising on the topic at a professional level. Comfort applying multi-page rubrics consistently across long batches. Clear written reasoning that cites methods, papers, or worked examples. Reliable async availability for at least 10 hours per week.