Remote Math SME for AI Benchmarking (Japanese)

LILT (Production); United States; A distancia; USD 83.000 - 165.000; A tiempo parcial

Ventajas ofrecidas por este puesto de trabajo

Flexible scheduling

Remote collaboration

Competitive rates

Descripción de la vacante

LILT is seeking experienced mathematics professionals to contribute to a cutting-edge AI benchmarking project in the target language. As a Subject Matter Expert, you will create and review high-quality mathematical scenarios that test AI systems in locale-specific contexts.

You will develop domain tasks, apply clear scoring rubrics, review submissions for accuracy and regulatory alignment, and provide expert feedback to help craft gold-standard solutions.

Formación

• Native in the target language with strong professional English proficiency.
• 5+ years of experience in Mathematics (e.g. applied mathematics, probability and statistics, computational mathematics and physics).
• Strong knowledge of target local frameworks.
• Ability to write and evaluate professional-grade mathematics content in the target language with high attention to detail.

Responsabilidades

• Create realistic, domain-specific tasks in target language reflecting local mathematics practices.
• Adapt and apply clear scoring rubrics to evaluate AI-generated and human responses.
• Review and score submissions for accuracy, regulatory alignment, and professional quality.
• Provide expert feedback and contribute to high-quality “gold standard” solutions.

Conocimientos

Native in target language

English proficiency

Mathematics experience

Local frameworks

Mathematics content writing

Descripción del empleo

LILT is seeking experienced mathematics professionals to contribute to a cutting-edge AI benchmarking project in the target language. As a Subject Matter Expert, you will create and review high-quality mathematical scenarios that test AI systems in locale-specific contexts.

You will develop domain tasks, apply clear scoring rubrics, review submissions for accuracy and regulatory alignment, and provide expert feedback to help craft gold-standard solutions.