Remote AI Math Scientist for Frontier Model Evaluation

Turing; Turkey; Remote; TRY 1,365,000 - 2,729,000; Full time

Job summary

Turing invites talented contractors to contribute to cutting-edge AI evaluation by designing challenging physics problems and generating gold-standard data. You will collaborate with LLM researchers to align tasks with evaluation goals and push the boundaries of symbolic manipulation, abstraction, and multi-step reasoning.

Ideal candidates have a strong mathematics background (PhD preferred) and can work 4 hours daily in a remote-first setup, with overlap for PST.

Qualifications

• Strong analytical, research, and problem-solving skills with excellent English comprehension.

Responsibilities

• Design physics problems to test the boundaries of large language models.
• Create clear, high-quality, step-by-step solutions with detailed and articulated reasoning.
• Collaborate with LLM researchers to align task designs with evaluation goals and target areas where models struggle.
• Define and build new evaluation benchmarks across physics curricula from undergrad to PhD topics.

Skills

Analytical skills

Research skills

Problem solving

English comprehension

Written communication

Independent work

Education

PhD in Mathematics

Job description

Turing invites talented contractors to contribute to cutting-edge AI evaluation by designing challenging physics problems and generating gold-standard data. You will collaborate with LLM researchers to align tasks with evaluation goals and push the boundaries of symbolic manipulation, abstraction, and multi-step reasoning.

Ideal candidates have a strong mathematics background (PhD preferred) and can work 4 hours daily in a remote-first setup, with overlap for PST.