AI Safety Evaluator / AI Annotator (Freelance)
In this role, I evaluated AI model responses for safety, accuracy, and policy compliance. I identified toxic content, bias, and potential data leaks in AI-generated outputs. I conducted red teaming to test vulnerabilities and contributed to improved model performance and ethical alignment. • Evaluated multiple model outputs to determine reliability and safety. • Participated in stress testing for model robustness. • Helped ensure model adherence to legal and ethical guidelines. • Enhanced model reliability through quality audits.