Una candidatura completa in un minuto
Curriculum e lettera di presentazione personalizzati, pronti da inviare.
Crossing Hurdles is seeking a highly-qualified mathematics-focused evaluator to design and test reasoning capabilities of large language models. The role requires producing clear, structured, step-by-step solutions and novel scenarios to probe AI reasoning, along with detailed annotations for model improvement.
Candidates should hold a PhD in Mathematics and demonstrate strong analytical skills, plus experience in AI evaluation or related analytical roles.
Commitment: 40 hours/week, with at least 4 hours overlap during PST business hours