I am a PhD student in Computer Science currently based in Campinas, Brazil, where I conduct my research at the University of Campinas (UNICAMP). This blog is an extension of my academic life, but behind the papers, code, and experiments there is someone genuinely curious about how complex systems learn, fail, and adapt.

My background is in machine learning and computer vision, with several years of experience working on applied research problems that sit at the intersection of theory, engineering, and real-world constraints. During my doctoral studies, my work has increasingly focused on semantic segmentation under weak supervision, aiming to reduce the reliance on dense, fully annotated datasets while still producing robust and meaningful representations.

Prior to and alongside my PhD, I have worked extensively with seismic data, particularly in the context of seismic facies segmentation. This domain has shaped the way I think about machine learning research: data is noisy, labels are expensive and imperfect, and evaluation is rarely as clean as benchmark datasets suggest. I expect seismic applications to remain a recurring testbed for my research ideas and methodologies.

I am also the creator and technical lead of an open research framework developed within my academic context, aimed at supporting reproducible machine learning experimentation and scalable research workflows. This work reflects my focus on clean abstractions, extensibility, and the practical realities of running large experimental pipelines, and it continues to evolve alongside my research activities. The framework is openly available here.

I work primarily in Portuguese and English, with Portuguese being my native language and English used daily for research, writing, and collaboration. I also have foundational knowledge of Japanese, supported by JLPT N5 certification, and continue to study the language as a long-term personal and cultural interest.