Alcune informazioni sono riportate in lingua inglese.
Chi sono
I'm a self-taught AI evaluator focused on LLM testing, prompt behavior, workflow review, and structured-output reliability. I build hands-on local evaluation projects using Python, Ollama, GitHub Actions, and structured logging. My work centers on practical testing: prompt conflict, schema drift, output inconsistency, and prompt injection-related issues. I bring a practical, detail-oriented mindset and work best on small, clearly scoped reviews with honest reporting and clear communication.... Continua a leggere