AI Trainer Fellowship (Handshake AI)
Served as an AI Trainer Fellowship participant evaluating domain-specific prompts for large language model performance in image generation. Assessed scientific accuracy, clarity, and depth of model outputs within specialized subfields through expert review and feedback. Supported prompt development and independent evaluation research to improve downstream image generation understanding. • Developed and evaluated domain-specific prompts for LLM image generation • Analyzed LLM outputs for scientific accuracy, clarity, and depth • Provided expert review and feedback to improve model understanding • Conducted independent research to support prompt development and evaluation tasks