Hanna Bass

I am a former landscape architect turned AI prompt engineer and evaluator with over three years of hands-on experience designing and refining prompts, conducting rubric-based QA, and performing LLM testing including GPT-4 evaluations. I have developed and optimized 500+ prompts, authored documentation on prompt patterns and annotation workflows, and delivered consistent, high-quality evaluations while flagging bias, toxicity, and hallucinations to support responsible AI practices.

I collaborate closely with researchers and developers to debug failure cases, refine evaluation criteria, and mentor junior raters to improve team consistency. I hold certifications in Generative AI from Microsoft and Google and bring strong analytical thinking, technical troubleshooting, and a commitment to ethical, safety-focused NLP work.