Remote Math Expert for AI Model Benchmarking

Parailabs; Northern (KY); Hybrid; USD 90,000 - 130,000; Part time

Benefits offered by this job

Fully remote environment

Cutting-edge AI projects

Contractor engagement with potential续

Job summary

Turing, based in San Francisco with remote-friendly culture, seeks a mathematical thinker to design and solve advanced problems that probe the limits of large language models. You will craft clear, step-by-step explanations and work with LLM researchers to shape evaluation benchmarks across early undergraduate to PhD-level topics.

The ideal candidate holds a Master’s/Ph.D. in a quantitative field and demonstrates excellent analytical and communication skills for remote collaboration with global

Qualifications

• Pursuing a Master’s/Ph.D./Postdoctoral degree in Mathematics, Applied Mathematics, Statistics, or a related field.
• Ability to analyze and solve complex math problems with a structured and logical approach; explain concepts clearly using simple language, visuals, and examples.
• Strong research and analytical skills.
• Excellent written and verbal communication for remote collaboration.

Responsibilities

• Design and solve challenging math problems to probe the limitations of large language models.
• Develop high-quality, step-by-step solutions with clear and rigorous reasoning.
• Collaborate with LLM researchers to align problem types with evaluation goals.
• Contribute to defining new evaluation benchmarks spanning undergraduate to PhD-level topics.

Skills

Analytical thinking

Clear math explanations

Structured communication

Independent/Remote work

Research ability

Feedback capability

Education

Master's/PhD in Mathematics

Postdoctoral degree (optional)

Graduate studies in Applied Math/Statistics

Job description

Turing, based in San Francisco with remote-friendly culture, seeks a mathematical thinker to design and solve advanced problems that probe the limits of large language models. You will craft clear, step-by-step explanations and work with LLM researchers to shape evaluation benchmarks across early undergraduate to PhD-level topics.

The ideal candidate holds a Master’s/Ph.D. in a quantitative field and demonstrates excellent analytical and communication skills for remote collaboration with global