25 Aug 2026
Starting this blog
I’ve wanted a place to write down what I’m learning for a while, mostly so I stop re-deriving the same idea three months later. This is that place.
Hi, I'm João.
I hold a Master's in Computer Science, and I'm looking to contribute to the field of Artificial Intelligence. Mostly, I want to make models less opaque and more interpretable, especially in medicine. I like to think that by looking inside these machines, we get a glimpse into our own minds too.
Projects
WASPI
An agentic LLM platform for equipment integrity and reliability analysis in the energy sector — reasoning over knowledge graphs built from maintenance records.
ELLME
A large language model project addressing bias and equity in healthcare, developed with Hospital Israelita Albert Einstein for Brazilian sociodemographic realities.
Publications
Faithfulness and Uncertainty Calibration of Large Language Models in Portuguese Medical Question Answering
2026 IEEE 39th International Symposium on Computer-Based Medical Systems (CBMS)
Analysis of Automated Document Relevance Annotation for Information Retrieval in Oil and Gas Industry
Proceedings of EMNLP 2025 — Industry Track
The Bode Family of Large Language Models: Investigating the Frontiers of LLMs in Brazilian Portuguese
Journal of the Brazilian Computer Society · 2025