Mathematics Phd - Ai Evaluation Expert

Mercor; San Francisco (CA); Hybrid; GBP 62,000 - 92,000; Part time

Job summary

Mercor seeks a Mathematics PhD Coding Expert for a 6-week remote contract. The role requires developing datasets and prompts to challenge frontier AI models, with tasks graded against defined criteria and calibrated against model performance. You will work independently, contributing to AI research at an elite level.

Immediate start, 20+ hours/week. Strong background in numerical linear algebra or related fields, and proficiency in Python or R, plus GitHub and Docker experience, are essential.

Qualifications

• PhD in mathematics, applied mathematics, computational mathematics, or closely related field.
• Depth in at least two subdomains: numerical linear algebra, computational mechanics, computational finance.
• Proficiency in Python or R for scientific computing.
• Experience with Git/GitHub and Docker.

Responsibilities

• Source original material from published papers, Kaggle datasets, open-source repositories, or self-designed scenarios.
• Write scientific prompts based on sourced input to challenge frontier models.
• Build grading criteria that define correct answers for scientific tasks.
• Calibrate tasks against frontier models, ensuring tasks ship only when strong models fail more often than succeed.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

Asynchronous work

Scientific computing mindset

Education

PhD in mathematics

Tools

Python

R

Git/GitHub

Docker

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.

Position: Mathematics PhD Coding Experts
Type: Contract
Compensation: $70/hour
Location: Remote
Duration: 6 weeks
Commitment: 20+ hours/week

Role Responsibilities

• Source original material from published papers, Kaggle datasets, open-source repositories, or self-designed scenarios.
• Write scientific prompts based on sourced input to challenge frontier models.
• Build grading criteria that define correct answers for scientific tasks.
• Calibrate tasks against frontier models, ensuring tasks ship only when strong models fail more often than succeed.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

Must-Have

• PhD in mathematics, applied mathematics, computational mathematics, or a closely related field.
• Demonstrated depth in at least two subdomains: numerical linear algebra, computational mechanics, computational finance.
• Working proficiency in Python or R for scientific computing.
• Comfortable with Git/GitHub and running code in Docker.

Preferred

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

Start Date

• Immediate

Interview Process

• An 25-minute conversational interview covering your background, experience, and motivations.
• Follow up within a few days with next steps and onboarding.

Application Process (Takes 20–30 mins to complete)

Resources & Support

• For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
• For any help or support, reach out to: [e-mail]