AI Evaluator and Tester, Prolific platform
As an AI evaluator and tester on the Prolific platform, I was responsible for assessing AI-generated videos and images for quality and accuracy. My role also included evaluating whether AI models adhered to user prompts and followed guidelines faithfully. Additionally, I contributed to projects verifying the safety of AI models in conversation and compliance with protocol. • Conducted ratings of AI output in video and image formats. • Evaluated prompt adherence in LLM/AI system outputs. • Participated in model safety assessments for conversational AI. • Provided comprehensive feedback on model quality and compliance.