AI Training Specialist / Evaluator
As an AI Training Specialist, I executed Reinforcement Learning from Human Feedback (RLHF) tasks focused on large language model (LLM) performance in STEM and technical subjects. My role included evaluating and rating AI-generated outputs for technical accuracy, safety, and reasoning quality. I also designed prompts and performed quality assurance to detect hallucinations and improve model reliability. • Conducted RLHF data labeling tasks in STEM and technical domains. • Designed and refined complex prompts for model evaluation. • Provided detailed feedback on model-generated outputs to improve accuracy. • Ensured technical content was free from hallucinations and safety concerns.