Remote Math Research Scientist for AI Evaluation

Crossing Hurdles; United States; Remoto; USD 120.000 - 180.000; Tempo pieno

Descrizione del lavoro

Crossing Hurdles is seeking a researcher to design and solve challenging mathematics problems that test the capabilities and limitations of large language models. You will create clear, accurate, high-quality step-by-step solutions with detailed reasoning and develop gold-standard data for AI model training and evaluation, collaborating with LLM researchers to align tasks with evaluation goals.

The role emphasizes tackling problems from advanced undergraduate to PhD-level concepts in a

Competenze

• PhD in Mathematics or an equivalent technical field.
• Strong foundation in advanced mathematics and reasoning.
• Ability to explain complex concepts with clear, structured step-by-step reasoning.

Mansioni

• Design and solve challenging mathematics problems testing LLM capabilities.
• Create clear, accurate, high-quality step-by-step solutions with detailed reasoning.
• Develop gold-standard mathematical data for AI model training and evaluation.
• Collaborate with LLM researchers to align task designs with evaluation goals.
• Target areas where AI models struggle, including symbolic manipulation, abstraction, and multi-step reasoning.
• Help define evaluation benchmarks covering mathematics from undergraduate to PhD levels.
• Construct novel mathematical scenarios and evaluate complex reasoning pathways.

Conoscenze

Analytical thinking

Mathematical reasoning

Problem-solving

Structured written communication

English comprehension

Independent work

Self-motivation

Creative thinking

Lateral thinking

Research skills

Formazione

PhD in Mathematics or equivalent technical field

Descrizione del lavoro

Crossing Hurdles is seeking a researcher to design and solve challenging mathematics problems that test the capabilities and limitations of large language models. You will create clear, accurate, high-quality step-by-step solutions with detailed reasoning and develop gold-standard data for AI model training and evaluation, collaborating with LLM researchers to align tasks with evaluation goals.

The role emphasizes tackling problems from advanced undergraduate to PhD-level concepts in a