AI Trainer & LLM Evaluator
I undertook AI/LLM training tasks involving Reinforcement Learning from Human Feedback (RLHF) and evaluated large language model (LLM) outputs. My work focused on assessing and ranking responses to improve model output quality. I also designed and tested prompts for AI applications. • Evaluated and ranked LLM outputs for quality and relevance • Improved AI model response quality with RLHF techniques • Conducted structured prompt engineering and testing • Adapted quickly to changing LLM evaluation requirements