AI Evaluator (freelance) for Indonesian Language and Chemistry at Outlier AI
Served as an AI Evaluator for Indonesian Language and Chemistry subjects in multiple LLM projects. The tasks included rating and comparing outputs from language models according to detailed guidelines and criteria. Completed over 120 task units across at least 6 projects, accumulating 40+ total hours of evaluative work.• Involved rigorous evaluation of AI model responses for accuracy, relevance, and adherence to given prompts. • Focused on both general textual tasks in Indonesian and technical content related to Chemistry. • Delivered comprehensive feedback to inform further model training and improvement. • Enhanced subject-specific evaluation skills through repeated task iterations and refinement cycles.