Prompt Engineer & AI Evaluator
As a Prompt Engineer & AI Evaluator, I designed and tested prompts for text generation, summarization, and Q&A tasks. I evaluated model responses based on helpfulness, harmlessness, and honesty using the HHH framework. My contributions included creating adversarial prompts and red-teaming test cases to identify model failure modes. • Developed and benchmarked prompts for LLM performance • Assessed hallucinations, alignment gaps, and quality issues • Authored test cases for robust red-teaming • Supported improvements in text generation and summarization evaluations