Distributed Systems for AI
Applying fundamental systems principles to build reliable, secure, and sustainable AI infrastructure.
University of Alberta
Laboratory for Impact-Conscious Distributed Systems
Advancing reliable, secure, and sustainable distributed computing.
We are recruiting! LIDS has openings for PhD/MSc students and postdoctoral researchers.
At LIDS, we develop systems and algorithms to make distributed computing more reliable, secure, and sustainable. Our impact-conscious approach considers the broader consequences of systems design and operational decisions, including their implications for reliability, security, performance, resource efficiency, and environmental sustainability. We investigate these challenges across diverse computing environments, from hyperscale cloud and AI data centers to resource-constrained edge sites and IoT devices.
Our current research lies at the intersection of distributed systems, artificial intelligence (AI), and sustainable computing, spanning two complementary directions:
AI for Distributed Systems
Developing AI methods to improve the reliability, security, and efficiency of distributed systems.
Across both directions, we combine empirical systems research with mathematical modeling and techniques from machine learning, causal inference, optimization, graph theory, and queueing theory. Our goal is to advance the foundations of distributed systems by developing novel abstractions, mechanisms, and algorithms that address emerging challenges as hardware, software, and applications continue to evolve.