• Design realistic scenarios in your target language or English grounded in operational contexts • Adapt structured evaluation rubrics • Review AI and human-generated responses for factual accuracy, quality, cultural appropriateness, and operational realism • Contribute to “gold standard” solutions reflecting best practices across the target locale and domain

• Create realistic, domain-specific tasks in the target language reflecting local natural sciences 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

• Design realistic healthcare and social assistance scenarios in the target language reflecting the target locale clinical and administrative settings (e.g., patient intake, care coordination, hospital operations, nursing workflows) • Develop structured evaluation rubrics for assessing clinical reasoning, administrative accuracy, and patient safety considerations • Review and score AI and human-generated responses for medical correctness, operational feasibility, and communication quality • Contribute to “gold standard” answers aligned with best practices in healthcare delivery and patient safety • Ensure cultural and contextual appropriateness in target language healthcare environments, including hospital workflows and regulatory expectations.

• Create realistic, domain-specific tasks in the target language that reflect 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