João Vitor Moreira

Bio

Experienced in AI development, data science, and software engineering, with hands-on work in content moderation and abuse detection systems. I design and evaluate models that balance safety and user experience, including human-in-the-loop workflows and bias-aware approaches. My research explores how information propagates across social networks and how bias emerges in AI-driven learning environments. Motivated to work in Trust & Safety to build scalable systems that protect users and promote healthy online communities.