AI Output Evaluator & Prompt Engineer
Evaluated AI-generated text and video outputs for accuracy, relevance, bias, and safety. Provided structured feedback and flagged hallucinated or non-compliant content to refine language and vision-language models. Designed, tested, and iterated prompts for various AI tasks ensuring clarity and compliance.• Conducted structured evaluations of AI outputs and documented findings. • Flagged bias, safety risks, and hallucinations in responses. • Crafted and refined prompts for LLM and VL models. • Collaborated with teams to maintain high standards in evaluation protocols.