AI Trainer / AI Data Specialist
Text
RLHFI trained and refined Large Language Models by utilizing prompt engineering, ranking responses, and implementing reinforcement learning from human feedback (RLHF). I conducted comprehensive data annotation and labeling on diverse text and technical datasets to help improve model performance. My work included detailed evaluation of AI outputs for accuracy, reasoning, safety, and contribution to ongoing improvements through feedback. • Applied prompt engineering and RLHF on text data for model refinement. • Labeled and annotated AI outputs for correctness and quality. • Performed quality checks and gave targeted feedback to enhance AI reasoning and safety. • Collaborated remotely with global teams using a variety of annotation tools.
2023 - Present