Legal Subject Matter Expert (SME) | AI Training / LLM
As a Legal Subject Matter Expert at, I specialize in legal task design and model evaluation for AI training. I build and assess complex legal prompts, focusing on Deep Research, reasoning, and adversarial tasks covering Argentine and Latin American law along with comparative analysis. My work involves applying structured scoring rubrics, performing side-by-side model rankings, and auditing model outputs to ensure legal reliability and accuracy. • Designed and scored prompts for Large Language Model (LLM) training in legal contexts. • Assessed factual reliability, jurisdictional accuracy, and legal reasoning of model responses. • Carried out side-by-side ranking, comparison, and auditing model failure modes. • Focused on identifying and correcting legal hallucinations in generative AI model outputs.