AI Systems Developer and Prompt Engineer
As an AI Systems Developer and Prompt Engineer, I performed high-volume evaluation of language model outputs within an AI personal operating system project. I designed, iterated, and tested hundreds of AI prompts and systematically evaluated the quality of generated responses for accuracy, tone, relevance, and safety. My work included identifying model errors and documenting structured feedback to improve system behaviors. • Directly responsible for prompt writing, AI output evaluation, and feedback documentation • Labeled model errors including hallucinations, refusals, and output inconsistencies across diverse tasks • Applied evaluation rubrics for instruction-following discipline and consistency • Assessed text and code outputs across business, technical, and creative subject matter