Lean Engineer, Formal Mathematics (Lean 4, Mathlib, Theorem Proving)

AuraOne, Inc.; United States; Remote; USD 124,000 - 152,000; Part time

Benefits offered by this job

PhD/postdoc experience

AI tooling review

Multilingual fluency

Job summary

AuraOne, Inc. seeks a Lean Engineer for Formal Mathematics to review AI outputs, reproduce key steps, and document the correct reasoning for model training. This remote contractor role requires strong math expertise and the ability to assess proofs and arguments across Lean 4 and Mathlib.

You will reproduce derivations, flag errors, and capture corrected methods to support the modeling team. Flexible async availability and high-quality written work are essential.

Qualifications

• Graduate-level training in mathematics or a closely related field.
• Hands-on experience publishing, teaching, or advising on the topic at a professional level.
• 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 Lean Engineer, Formal Mathematics (Lean 4, Mathlib, Theorem Proving) 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 or closely related field

Job description

Lean Engineer, Formal Mathematics (Lean 4, Mathlib, Theorem Proving) 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 Lean Engineer, Formal Mathematics (Lean 4, Mathlib, Theorem Proving) 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 Lean Engineer, Formal Mathematics (Lean 4, Mathlib, Theorem Proving) 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–$110 / hr