AI Math Evaluator & Reasoning Specialist

Crossing Hurdles; Indonesia; Presencial; IDR 894.614.000 - 1.431.383.000; Jornada completa

Descripción de la vacante

Crossing Hurdles is seeking a mathematics-focused evaluator to design and solve challenging problems that test the reasoning capabilities of large language models. You will produce clear, step-by-step solutions with rigorous explanations. Ideal candidates hold a PhD in Mathematics, demonstrate strong analytical and research skills, and provide detailed, structured feedback and annotations to improve AI evaluation and quality assurance.

Formación

• PhD in Mathematics or an equivalent technical field with strong analytical, research, and problem-solving skills.
• Strong foundation in Mathematics, spanning advanced undergraduate through graduate and PhD-level concepts.
• Ability to break down complex mathematical concepts into clear, structured, step-by-step reasoning.
• Strong written communication skills with the ability to provide detailed feedback and annotations.
• Prior experience in AI evaluation, data annotation, content review, quality assurance, mathematical research, or related analytical roles is preferred.

Responsabilidades

• Design and solve challenging Mathematics problems that test the reasoning and problem-solving capabilities of large language models.
• Create clear, high-quality, step-by-step solutions with detailed and well-structured reasoning.
• Develop novel mathematical scenarios that evaluate complex reasoning pathways and identify areas where AI models struggle.
• Provide detailed annotations and constructive feedback to improve model performance and evaluation quality.

Conocimientos

Analytical skills

Problem-solving

Structured reasoning

Clear written communication

Educación

PhD in Mathematics or equivalent

Descripción del empleo

Crossing Hurdles is seeking a mathematics-focused evaluator to design and solve challenging problems that test the reasoning capabilities of large language models. You will produce clear, step-by-step solutions with rigorous explanations. Ideal candidates hold a PhD in Mathematics, demonstrate strong analytical and research skills, and provide detailed, structured feedback and annotations to improve AI evaluation and quality assurance.