Mírian Silva

Research Interest

• In addition to my engineering background, I have research interests in areas such as fairness and bias in AI, within the broader context of AI ethics, as well as AI for Good and interdisciplinary work at the intersection of AI and the social sciences. On the engineering side, my professional interests include AI/ML engineering, large-scale model evaluation, ML reliability and robustness, and applied AI engineering and prototyping. If you are working on these or related topics and are seeking research collaborations, feel free to reach out to me.

TLDR: Academic and Professional background

• I've been an AI Engineer at IBM Research over 4 years. As part of the AI Models Team that works alongside the Granite Models Team. I've been collaborating closely with product managers and researchers to evaluate performance of proprietary models.
  • Currently responsible for leading initiatives focused on Granite models' quality over time, and also developing algorithms/tools that improve users' and clients' generative AI applications.
  • I've also worked alongside MIT-IBM Watson AI Lab, mainly doing collaborative research with student and staff researchers, primarily on research related to LLM evaluations, validation process, prompt engineering, and model improvements for distinct applications.
  • Outstanding Open-source projects and internal award-winning: github.com/IBM/ibm-generative-ai. A Python library built on IBM's large language model REST interface to seamlessly integrate and extend this service in Python programs. Initial author and maintainer until 0.2.6v.
  • Research publications from my work, can be found in my page at the IBM Research profile.
• I recently received a Master's Degree in Computer Science at the Federal University of Minas Gerais (UFMG, Brazil), with research based on AI focused on machine learning 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).
  • Mírian Silva. (2024). A study of the nuances of ai fairness development in practice: A framework for designing bias mitigation interventions (Master’s Thesis, Federal University of Minas Gerais (UFMG), Belo Horizonte, Brazil). Available at http://hdl.handle.net/1843/78989.
• 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.