I am currently a Ph.D. student in Mechanical Engineering, at Federal University of Rio de Janeiro, with a focus on applying generative models to scientific applications, in particular using diffusion models for the flow-accurate reconstruction of fluid-containing porous media microstructure.Before that, I worked consists of developing and coupling physicochemical and fluid models to predict inorganic scaling (mainly calcium carbonate scaling), developing machine learning-based probabilistic inference methods in settings where evaluation of models is relatively expensive, developing data-driven methods for predicting, road traffic data, developing inference methods for radiation dose estimation, and using deep learning techniques for solving partial differential equations, in particular ones used in finance modeling.Personal interests consist of understanding the future and possible risks of artificial intelligence, the possible ways of mitigating those risks, and the internal nature of these systems. I also study AI Alignment, participating both in the AI Safety Camp 2023, Part I of MATS 2022 Winter Program, as well as a fellow in the AI Safety, Ethics, and Society course in 2024. I also participated as a mentor in the Alinha Hacka 2023 at Ribeirão Preto, and Machine Learning for Good Brazil 2024, in São Paulo. I am also involved in the Effective Altruism community, facilitating the EA In-Depth program Oct/Nov 2022, and participating in the EA Community in Brazil, particularly Rio de Janeiro.Finally, I'm interested in philosophy (especially philosophy of mind, ethics, and metaphysics) and mathematics in general.Some of my work can be found in:GitHub: https://github.com/dfnaiffPersonal Website: https://dfnaiff.github.io/Google Scholar: https://scholar.google.com/citations?user=UgDxpKgAAAAJ&hl