About The Opportunity قائد/ة مشروع تكييف المعايير المرجعية لتقييم الذكاء الاصطناعي للسياق الخليجي

نبحث عن قائد/ة مشروع لإدارة فريق من الخبراء الخليجيين في تطوير محتوى تقييمي عالي الجودة باللغة العربية الفصحى الحديثة.

LILT adapts benchmarks into Modern Standard Arabic for the GCC market. Tasks are delivered as an Arabic task statement, a scoring rubric, human & LLM submission scores and a gold solution. The output includes published datasets and research papers.

This project lead role is for a specific benchmark. The pilot is complete and we are scaling to full production. The project lead will work with GCC-based domain experts organized into pods by domain. The lead will be provided with production support to help organize logistics.

What Youll Deliver

• Onboard Task Creators and Reviewers: rubric methodology, GCC adaptation guidelines, scoring tools and gate-tracking workflow.
• Gate tasks for quality and provide feedback at all ...