Mírian Silva

Mírian Silva

About me A girl who likes to travel, buy more books than read, and watch superheroes and horror movies, with a subscription to all streams so I don't miss any TV shows. I don't actively consume YouTube, but I enjoy videos like 3Blue1Brown. I recently became a Jedi (MSc). :)

TLDR: Academic and Professional background

  • I've been an AI Engineer at IBM Research since 2021. I work with the AI Models Team and the MIT-IBM Watson AI Lab, mainly programming cool stuff related to foundation models, generative AI, and AI engineering.
  • I recently received a Master's Degree in Computer Science at the Federal University of Minas Gerais (UFMG, Brazil), with research on AI fairness, bias mitigations, and evaluation practices. I also hold a B.Sc in Computational Mathematics, a degree based on computer science and applied mathematics, from the same university (UFMG).
  • Previous Research Fellow and Visiting Scholar at the University of California, Berkeley, in the Berkeley Equity and Access in Algorithms, Mechanisms, and Optimization (BEAAMO) Research Group. Working on auditing and evaluating algorithmic tools and evidentiary statistical software used in criminal legal systems. Supervised by Prof. Rediet Abebe, Ph.D.
  • I usually organize workshops at top-tier AI conferences such as NeurIPS, ICML, and NAACL, as chair organizer of Black in AI affinity groups.

Research Interest

  • Fairness and Bias in AI, Ethics & Trustworthy AI. Interdiciplinary research in AI and Law, AI and Social Sciences, AI and Public Policy are currently my main topic of interest. If you are working on these or related topics, and search for collaborations feel free to reach out to me.