Keynote Speakers

Pedro Pedreira
Software Engineer at Meta

Short-bio: Pedro Pedreira is a Software Engineer at Meta. In his 10+ year tenure, he has led a series of Data Infrastructure projects in collaboration with the research and open-source community. Pedro leads the Velox program, a cross-organizational effort involving 20+ companies aimed at unifying execution engines using an open-source library, in addition to related efforts regarding data processing at scale, focused on accelerating both traditional Analytic and novel ML workloads. In the past, he worked on log analytics engines (such as Scuba), and created Cubrick, an in-memory analytical DBMS. Pedro holds a Ph.D, M.Sc, B.Sc in Computer Science from the Federal University of Parana (UFPR), in Brazil.

AbstractData management system design has evolved over the last decade. The traditional monolithic model of developing vertically integrated systems resulted in a fragmented landscape dominated by inconsistent user APIs and SQL dialects; this has limited reuse among data systems and ultimately slowed down innovation. In this lecture, I will present the new composable data system stack that has emerged in the community, largely driven by open source. I will highlight how projects such as Velox, Prestissimo, Nimble, Gluten, and others created by our team at Meta and by the open-source community are improving both the efficiency and engineering efficiency of developing data systems, while providing a framework more suitable for evolving hardware platforms.


Angelo Brayner
Professor at UFC

Short-bio: Angelo Brayner holds a master’s degree in Computer Science from the State University of Campinas (UNICAMP) and a PhD in Computer Science from the Universität Kaiserslautern, Germany. He is an adjunct professor at the Federal University of Ceará, and has served as a visiting professor at the University of Stuttgart. He is the author and co-author of several books, including Transaction Management in Multidatabase Systems, published by Shaker-Verlag, Germany, and #8203;#8203;Developments and Applications for ECG Signal Processing, published by Elsevier. He was one of the recipients of the 2020 Annual Prize of the Cuban Academy of Sciences and the CITMA Prize of the Province of Santiago de Cuba, the latter awarded by the Ministry of Science, Technology and Environment of the Caribbean country. He coordinated the working group of the Brazilian Computer Society, which developed the curricular references for undergraduate courses in Data Science. Prof. Angelo Brayner is the author of more than 100 articles published in journals, such as ACM Computing Surveys, and international and national conferences.