AI Trainer, Outlier
Served as an AI Trainer creating prompts to test the accuracy and factuality of generative AI models. Conducted analytics on both contributor assessments and the performances of generative AI systems. Checked pre-generated responses and prompts to evaluate the conversational and role-playing capabilities of Gen AI models. • Created comprehensive prompts for systematic AI evaluation. • Analyzed contributor assessments for performance insights. • Evaluated AI-generated responses across various use cases. • Contributed to quality control of Gen AI outputs.