Mathematician - AI Model Evaluator (opens in new tab)

SOA

United States

Remote

USD 55,000 - 172,000

Part time

11 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Flexible project selection
Own schedule
Remote work from home
Hourly pay up to $40-$125 USD with on‑
Bonuses on high-quality work

Job summary

DataAnnotation is seeking a Mathematician - AI Model Evaluator to design challenging mathematical problems that current AI models still struggle with. You will judge correctness versus plausibility and build the tooling to prove it in a research-focused, remote role.

You will design, test, and validate complex tasks, ensuring accuracy as ground truth for model scoring. Strong math stats background and coding ability are essential.

Qualifications

  • Fluent in English, native or bilingual level.
  • Active research background in mathematics or statistics at graduate/postdoc/academic or industry level.
  • Strong coding skills; comfortable using a terminal and Python for research.

Responsibilities

  • Design complex mathematical tasks for AI evaluation.
  • Define correct answers and required standards for model evaluation.
  • Test, validate, and document tasks so others can reproduce results.
  • Write clear, step-by-step solutions that can be reviewed by researchers.
  • Identify where model reasoning breaks and flag invalid steps or unjustified conclusions.
  • Collaborate across numerical analysis, optimization, probability and statistics, and ML domains.

Skills

English fluency
Coding proficiency

Education

Active research background in mathematics or statistics

Tools

Python
Docker

Job description

DataAnnotation is looking for a Mathematician - AI Model Evaluator to design mathematical problems that today's leading AI models still get wrong. Models are fluent enough to produce an answer that looks right and a derivation that reads well. You bring the judgment to tell the difference between the two, and the tooling to prove it.

This is a new and growing area for our company, focused on teaching AI to reason correctly rather than plausibly. The work combines deep mathematical knowledge with strong coding skills: you design, test, and validate complex tasks yourself. Your task and your solution become the ground truth a model is scored against, so accuracy is the entire job.

Advantages of contracting with us:
  • You will be able to choose which projects you want to work on and when
  • You work on your own schedule, on your own computer, from the comfort of your own home
  • Projects are paid hourly up to $40-$125 USD per hour, with bonuses on high-quality work
Responsibilities:
  • Design complex mathematical tasks in your area of expertise
  • Define what a correct answer looks like and the standard a model has to meet
  • Test and validate the task yourself before you submit it
  • Write a step-by-step solution another researcher could reproduce
  • Design tasks a model cannot solve by replaying a known result, and flag where its reasoning breaks: invalid steps, unstated assumptions, right answers reached by wrong work
  • Work across numerical analysis, optimization, probability and statistics, applied analysis, and scientific machine learning
Qualifications:
  • Fluency in English (native or bilingual level)
  • An active research background in mathematics or statistics: advanced graduate student, postdoc, academic researcher, or industry practitioner
  • Strong coding skills. You write Python and work comfortably at a terminal as part of your research, not as a side interest
  • Familiarity with reproducible or containerized environments such as Docker is a plus
  • Note: Payment is made via PayPal. We will never ask for any money from you. PayPal will handle any currency conversions from USD. Only applicants in Australia, Canada, Ireland, New Zealand, the United Kingdom, and the United States will be considered for this role. This is an independent contractor position.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Scientific Machine Learning Researcher - AI Trainer
Scientific Machine Learning Researcher - AI Trainer

DataAnnotation • United States

Remote
CAD 78,000 - 243,000
Choose projects and schedule
Work from home on your own computer
Pay per hour USD 40–125 with bonuses
Mathematician - AI Model Evaluator
Mathematician - AI Model Evaluator

SOA • United States

Remote
USD 55,000 - 172,000
Remote Mathematician - AI Model Evaluator & Problem Designer
Remote Mathematician - AI Model Evaluator & Problem Designer

SOA • United States

Remote
USD 55,000 - 172,000
Flexible project selection
Own schedule
Remote work from home
+2
Mathematician for AI Reasoning & Ground-Truth Tasks
Mathematician for AI Reasoning & Ground-Truth Tasks

DataAnnotation • United States

Remote
CAD 78,000 - 243,000
Choose projects and schedule
Work from home on your own computer
Pay per hour USD 40–125 with bonuses
Mathematical Modeler - AI Trainer
Mathematical Modeler - AI Trainer

DataAnnotation • Town of Montana (WI)

Remote
USD 55,000 - 172,000
Flexible work
Remote work
Project-based workload
Mathematical Modeler - AI Trainer
Mathematical Modeler - AI Trainer

DataAnnotation • Colorado

Remote
USD 55,000 - 172,000
Flexible, remote work
Project-based engagement
Applied Mathematician - AI Trainer
Applied Mathematician - AI Trainer

DataAnnotation • United States

Remote
USD 55,000 - 172,000
Flexible schedule
Remote work
Numerical Analyst - AI Trainer
Numerical Analyst - AI Trainer

DataAnnotation • Michigan

Remote
USD 55,000 - 172,000
Flexible, remote projects
Numerical Analyst - AI Trainer
Numerical Analyst - AI Trainer

DataAnnotation • Alabama

Remote
USD 55,000 - 172,000
Remote work
Flexible hours
Performance-based pay
Mathematics Expert (LATAM & Europe)
Mathematics Expert (LATAM & Europe)

Anyone AI • United States

Remote
USD 45,000 - 65,000