In my independent AI Model Evaluation & LLM Response Assessment portfolio project, I compared Model A and Model B outputs in 20+ blind side-by-side evaluations. I assessed factual accuracy, logical consistency, and hallucinations using a fixed rubric.
I wrote detailed English rationales to justify output rankings and documented the prompts, model outputs, evaluations, and comparative analyses in an online portfolio. My background in formal logic and historical research informs my approach to evaluating claims and verifying sources.
At ilCartastorie | Museo Archivio Storico Banco di Napoli, I guided tours, more than 70% of them in English, and verified archival sources for historical content. I also managed production workflows and deliverables for Ginko Biloba, and co-founded Game Over, where I established operational workflows for video production and live events.
