Mathematics PhD – AI Evaluation Expert

Other • Senior • Remote • Full-time • Germany

Germany

Mercor is hiring a contract expert with a mathematics PhD to author scientific tasks and grading criteria for testing AI models. The work involves scientific Python programming and validating tasks against frontier models.

Stack

Docker Git GitHub Python

Responsibilities

▹Source material for tasks from papers and datasets
▹Write scientific prompts and tasks
▹Build grading/evaluation criteria
▹Calibrate tasks against frontier AI models

Requirements

▹PhD in mathematics, applied or computational mathematics
▹Depth in at least two subdomains (e.g. numerical linear algebra)
▹Working proficiency in Python for scientific computing
▹Comfortable with Git/GitHub and Docker

Nice to have

▹Publications in peer-reviewed journals
▹Prior scientific software or research engineering experience

Soft skills

Independent, asynchronous work styleAbility to meet deadlines reliably

What we offer

▹Remote work
▹Hourly compensation ($70/hour)

About the company

Mercor connects elite creative and technical talent with leading AI research labs, headquartered in San Francisco.

🛡️ Recently checked

✓ Posted 6 days ago
📋 This employer: 100% freshly verified (≤3 days) (378 active listings)

These signals come from our own daily check: when the listing appeared, and when we last saw it in the source. Not information from the employer, and not a guarantee that the role is still open.

Salary range

Not specified

Listing imported from an external source.

Work typeRemote

Location

Germany

TypeJob

Apply →

Source: Himalayas

🗺️ View on the map

More jobs at Mercor

All at this company (377) →

This listing comes from the employer's public careers page; the advertiser is responsible for its content. The summary is a machine-generated extract — check the original posting before applying.

Is this your company's listing? Request removal