Joao Tissingue

• Evaluated and refined Large Language Model (LLM) responses to improve accuracy, relevance, and safety across multilingual datasets. • Performed structured quality assurance testing on AI-generated text, images, and multimodal content. • Created and classified prompts to enhance model behavior and consistency. • Reviewed content according to AI safety and risk standards (text & image moderation frameworks). • Worked with dynamic LLM refinement workflows and AI evaluation pipelines.