Tallysnara A.

Tallysnara A. is a proficient AI Evaluation Specialist and Data Quality Analyst based in Cristalina, Goiás, Brazil, with a demonstrated history of expertise in fine-tuning Large Language Models (LLMs) and dataset auditing. Her experience includes evaluating over 15,000 AI-generated outputs, maintaining a 98.5% accuracy rate in Quality Assurance across complex RLHF benchmarking projects for Appen. She excels in detecting and mitigating model hallucinations, reducing error rates and policy violations by 25% through advanced prompt evaluation and red-teaming protocols. Tallysnara has a robust background in multimodal content evaluation, including image/video annotation and speech synthesis. Her governance and quality management skills include ensuring LGPD/GDPR compliance and enhancing data integrity. Tallysnara also has a legal background with a Bachelor of Laws degree and has engaged in professional training with Google in artificial intelligence.