Graduate Research Assistant
As a Graduate Research Assistant, I investigated human-AI interaction and feedback signal optimization for language model alignment. I developed evaluation frameworks for verifying AI-generated text correctness and coherence. My work centered on publishing research to improve AI reasoning through structured human feedback. • Researched RLHF signal engineering and effectiveness • Developed and applied evaluation criteria to AI outputs • Improved LLM alignment through data annotation and analysis • Authored reports and publications based on annotation experiments.