Advanced Mathematics LLM Evaluation Expert

About OpenTrain

OpenTrain is the #1 platform for people building careers in AI training and data labeling. We connect skilled contributors with specialized, cutting-edge projects so you can build a durable freelance career teaching AI.

OpenTrain AI is the hiring and contracting organization for this role. Creating an OpenTrain account is free and lets you find projects, build a unified portfolio, and apply quickly.

About AI training and why this work matters

AI training is the human side of building intelligent systems: people create, check, and refine examples that modern models learn from. Contributors directly shape how models reason, solve problems, and behave in real-world tasks.

This role focuses on evaluation and benchmark creation for mathematical reasoning—an area that helps improve model accuracy on multi-step, abstract, and proof-oriented problems.

The role

You will be an Advanced Mathematics LLM Evaluation Expert: designing original problems, solving them, reviewing model outputs, and contributing to new evaluation benchmarks. This is a remote contractor position for OpenTrain AI.

Workload: 20+ hours per week. Language: English. Employment types: contractor, part-time. This role is open worldwide.

• Employment: Contractor, part-time
• Weekly time expectation: 20+ hours/week
• Location: Remote, worldwide (English required)

What you'll do day-to-day

Your primary focus is creating and curating high-quality math evaluation content and assessing model outputs against rigorous mathematical standards.

• Design original, multi-step, and proof-based mathematics problems that push LLM reasoning limits
• Solve problems independently and write clear, logically structured solutions with step-by-step justifications
• Review model-generated solutions, identify mathematical errors, and provide precise corrective feedback and annotations
• Develop and validate Python-based solutions for computational tasks using approved scientific libraries
• Translate problems and proofs into formal language for theorem-prover tasks using Lean and evaluate formal proofs

Requirements

Candidates must demonstrate strong advanced-mathematics ability, excellent written communication, and the ability to work independently in a remote contracting role.

• Strong foundation in advanced mathematics at graduate or PhD level (algebra, analysis, topology, geometry, etc.)
• Ability to analyze and solve complex, multi-step mathematical problems with a structured approach
• Excellent written communication and skill at explaining math clearly in simple language
• Proven ability to review and annotate model-generated solutions with precise mathematical feedback
• Proficiency using a desktop or laptop with a reliable internet connection

Helpful background (not strictly required)

The following experience will help you contribute immediately and take on more advanced benchmark and theorem-prover tasks.

• Master's, PhD, or postdoctoral experience in Mathematics, Applied Mathematics, Statistics, or a related field
• Experience writing Python solutions and using scientific libraries for verification and computation
• Familiarity with theorem provers such as Lean and translating informal proofs into formal statements

How to apply and what to expect

Create a free OpenTrain account, build a profile that highlights your math background and technical skills, and submit your application for this role. OpenTrain AI handles contracting and project assignments.

We will evaluate applications based on math expertise, clarity of written solutions, and relevant tooling experience (Python, Lean). Specific project or assessment details will be shared after application.

• Application step: create an OpenTrain account (free) and submit your profile and materials
• Selection factors: demonstrated math ability, clear written solutions, Python or theorem-prover experience