RLHF Data Specialist
Handled text and image-based Reinforcement Learning from Human Feedback to fine-tune Large Language Models and output results from AI assistants. My experience comes from completing tasks by writing complex and specific-oriented prompts to test model capabilities. Also, I have experience in evaluating and grading various text outputs based on strict criteria to ensure that the responses are truthful, helpful, and accurate in terms of facts, formatting, and adherence to instructions and prompts