Technical AI Evaluator
Developed and refined advanced prompts for AI image and video generation while evaluating AI-generated code outputs. Performed annotation reviews and reinforcement learning feedback to support AI model improvement and ensure higher instruction-following quality. Conducted detailed quality checks for multimodal AI responses and educational datasets used for training and evaluation. • Evaluated code-generation performance in Python and Lisp-based tasks. • Reviewed annotations and provided RL feedback to reinforce desired behaviors. • Designed prompt strategies to improve coherence, output quality, and instruction adherence. • Performed quality checks for multimodal AI responses and educational datasets.