Remote AI Evaluation Specialist

Il y a 2 semaines

, La Réunion, France Crossing Hurdles Temps plein

Crossing Hurdles in France (La Réunion) seeks a detail-oriented evaluator to design self-contained AI evaluation tasks and rubrics, focusing on practical computer-based workflows.

You will observe AI agent behaviors, document observations in clear English, and iterate rubrics based on team feedback to ensure robust benchmarking.

Collaboration with the customer’s team will help drive continuous improvement in AI evaluation techniques.

#J-18808-Ljbffr