Lead AI Content Evaluator | Remote | 2023 – Present
Led AI content evaluation and ranking of model outputs for truthfulness, safety, and instruction adherence. Conducted deep-dive secondary research to verify factual accuracy and reduce hallucinations while improving relevance for global users. Maintained consistently high annotation quality across complex evaluation tasks. • Ranked responses based on rubric criteria (truthfulness, safety, instruction-following) • Verified AI-provided claims via detailed research • Collaborated to improve response quality and reduce hallucinations • Achieved 98%+ quality scores across evaluation work