Senior Psychology Expert - AI Trainer
In this role, I designed, evaluated, and refined ChatGPT/LLM prompts using RLHF and zero-shot evaluation methods. I developed natural language understanding (NLU) datasets aligned to ethical AI standards. I trained junior annotators on evaluation frameworks and quality assurance for AI model data. • Led RLHF and prompt engineering tasks for LLMs • Developed NLU datasets and evaluated for bias • Provided guidance and training to annotation teams • Maintained QA standards for labeled text data.