Ricardo Barbieri

I’m a highly technical AI specialist with 14 years at Banco Bradesco as a Systems/Data Analyst, specializing in automation, Excel/VBA, and modeling. I bring a strong engineering mindset to building measurable AI workflows.

Since 2022, I’ve focused on prompt engineering, multimodal evaluations, RAG systems, and LLM quality assurance. In my current role as a Multimodal AI Evaluator, I evaluate and refine multimodal models (text + image/video), with safety analysis and hallucination detection.

Before that, I worked as a Prompt Engineer & AI Evaluator (Outlier AI / DataAnnotation), performing LLm evaluation and reasoning tests, dataset creation and optimization, and edge-case stress tests. I also apply red-team practices against harmful content in complex scenarios.

Earlier in my career, I developed blockchain and smart contracts from 2013–2022, building solid foundations in Web3 and DeFi. Today, I combine that “systems” background with GenAI and evaluation to deliver reliable, high-performing AI solutions.