AI Data Quality Specialist, DataAnnotation (April 2025 – Present)
Evaluated AI-generated responses for factual accuracy and overall quality using multiple quality metrics. Performed judgment of source reliability during fact-checking and assessed instruction following, conciseness, relevance, groundedness, completeness, and safety. Wrote and refined evaluation rubrics and created prompts to test language models across tasks. • Fact-checking and source reliability assessment • Instruction following, conciseness, relevance, groundedness, and completeness evaluation • Safety and quality rating of AI responses • Rubric development and prompt design for model testing