
AI Tutor and L2 Quality Reviewer with experience training and evaluating large scale generative and multimodal AI systems across audio, video, and text. Skilled in prompt engineering, RLHF, SFT, human-in-the-loop evaluation, and adversarial testing to improve model accuracy, safety, and alignment. Proven in reviewing annotator outputs, generating high-quality training data, and identifying vulnerabilities such as jailbreaks and prompt injection.