Advanced Math Proof Expert

Send an email to stephaniemaryna.trafford@halogion.com with the Subject “Advanced Math Proof Expert” showing your interest in the role to get priority consideration.

At Halogion, we are an Independent member of Mercor referral partner program. We refer candidates to our partner that collaborates with world’s leading AI research labs to build and train cutting-edge AI models

We are seeking mathematically rigorous evaluators to contribute to an initiative in formal proof assessment and data quality assurance.

In this role, you will review, analyze, and score advanced mathematical proofs, ensuring logical correctness, completeness, and clarity across a variety of Olympiad-level problem types.

This position is ideal for individuals with a strong foundation in mathematical reasoning, attention to detail, and a passion for improving the next generation of intelligent reasoning systems.

Key Responsibilities

Evaluate formal mathematical proofs across Geometry, Combinatorics, Number Theory, and Algebra.

Assign correctness scores to the proof

Identify reasoning errors and concisely describe the reason for failure when applicable.

Maintain high levels of consistency, precision, and auditability across all annotations.

Support data quality, documentation, and structured feedback for continuous improvement.

Uphold all confidentiality, data handling, and deletion requirements post-project.

Minimum Requirements

BS or higher in Mathematics, Computer Science, or a closely related field.

Demonstrated experience with proof-based problem solving (e.g., USAMO, Putnam, IMO, or equivalent).

Strong command of mathematical logic and formal reasoning.

Prior experience evaluating, grading, or authoring mathematical proofs.

Excellent written communication and analytical precision.

Ability to work independently and meet deadlines reliably.

Preferred Qualifications

Experience in mathematical data annotation, AI reasoning evaluation, or educational content QA.

Familiarity with proof verification systems (Lean, Coq, Isabelle) or symbolic computation tools.

Background in academic competition problem design or evaluation.

Understanding of structured quality assurance workflows and calibration standards.

Clear and concise feedback writing for technical and mathematical content.