💡About me:
From a young age, I was fascinated by how complex systems work, a curiosity shaped by being the daughter of a Logic professor. Today, that early spark drives my research in Artificial Intelligence, Machine Learning, and model interpretability
🧠 Current focus:
- Developing, optimizing, and promoting the responsible use of AI agents powered by Large Language Models (LLMs)
- As a member of Future Lab (UFMG), I contribute to projects on AI interpretability, optimization, and decentralized intelligence — including a FAPEMIG-funded initiative on the Decentralization and Privacy of LLMs for National Technological Independence
- Deploying sentence embedding models for semantic analysis and sentiment/survival extraction in chatbots conversations
🔍 Research interests:
- Responsible & interpretable AI systems (explainability, fairness, safety)
- Knowledge Distillation, LoRA, and RAG applied to LLMs
- Semantic analysis and sentiment/survival modeling in human–AI interactions
- Nano-computation and the intersection between AI, physics, and hardware innovation
📚 Recent research topics & pre-publications:
- Measurement of Lead Temperature using NLP
- Quantification and Classification of Graphene Flakes in AFM Images using Machine Learning
- Towards Responsible, Interpretable, and Fair Safety Moderation of LLMs Across Demographic and Educational Contexts
- Heuristics for the Pit Sequencing Problem with Capacity Constraint (CPIT)
🧰 Tech Stack
- Toolkit: Python, SmolAgents, HuggingFace, TensorFlow, Keras, PyTorch, OpenCV, Scikit-learn, MLFlow, Docker, SHAP/LIME, Git, CI/CD
- Programming: C/C++, Python, Perl, PHP, Java
💬 Curious? Ask me about anything. I enjoy discussing AI, coding and computer science theory
📫 How to reach me: [email protected]
⚡ Fun fact: I'm passionate about cats, computer science, uncovering the laws of the universe and cooking reality shows!
📷 Check out my flickr: https://www.flickr.com/photos/188150337@N03/
