AI Model Evaluator & Prompt Engineer (Contract)
I created prompts and responses to train and test AI models, ensuring content adhered to guidelines in both English and Spanish. My work involved reviewing, rating, and multi-dimensional evaluation of AI outputs for safety, coherence, accuracy, and style. I compared and evaluated multiple AI systems to identify strengths, risks, and areas needing improvement. • Developed and curated text prompts and responses for AI model SFT tasks • Conducted rigorous evaluation and rating of model outputs on multiple criteria • Reviewed and provided feedback on prompt engineering and response quality • Compared system performance and documented risks and improvement recommendations