AI Training Specialist (Contract)
As an AI Training Specialist, I trained and fine-tuned large language models using Reinforcement Learning from Human Feedback. I evaluated model outputs for accuracy, safety, and helpfulness, providing structured feedback to guide improvements. I focused on optimizing prompt engineering and identifying policy violations. • Conducted RLHF evaluations on LLM outputs for quality assurance. • Applied structured rubrics to identify hallucinations and logical inconsistencies. • Optimized model performance through prompt rewriting and response refinement. • Maintained high output quality while managing high-volume task queues.