MSc candidate at the Federal University of Rio Grande (FURG), Brazil. My work asks how AI systems can be made trustworthy, and how people and AI should collaborate and remain accountable in public-sector decisions. I build and evaluate neuro-symbolic RAG systems that ground LLM outputs in verifiable institutional evidence.
Investigating how AI systems can be made trustworthy, transparent, and genuinely useful in high-stakes decision environments.
A neuro-symbolic RAG system for evaluating 220 Brazilian postgraduate programmes across three CAPES evaluation cycles.
PEPG 2.0 combines a deterministic symbolic scoring engine (8 KPIs) with FAISS-backed semantic retrieval and multi-LLM generation (GPT-4o, Gemini 2.5 Flash, DeepSeek). It turns black-box LLM predictions into transparent, auditable grade assessments anchored in verifiable CAPES documents, and showed substantially better groundedness than ungrounded baselines.
Research contributions in open government data, trustworthy AI and educational data mining.
A path from teaching and web development to applied AI research.
I'm open to PhD opportunities and research collaborations in AI governance, human–AI decision support and trustworthy AI. Feel free to reach out through any of the channels below.
Download Full CV →