University of Oxford, Department of Engineering Science reposted this
Super excited to be leading a new Scalable AI Systems project at University of Oxford, funded by Advanced Research + Invention Agency (ARIA). Our project aims to introduce a new interconnect for scalable AI systems that solves the communication bottleneck. By rethinking communication at multiple levels and bringing together different disciplines, our project will revolutionise the design of AI systems. We are now recruiting PhD students, postdoctoral researchers and a project manager to join our team of 16 researchers at University of Oxford, Department of Engineering Science. So if you are interested to research high performance interconnect with Nick McKeown, advanced memory architectures with Amro Awad, photonics and optical interconnect with Dominic O’Brien, Martin Booth and Patrick Salter or distributed AI systems with me, visit https://lnkd.in/eFaxfJmZ or contact us.
The history of computing hardware has been defined by scientists and engineers realising that radical new approaches are required to meet our technological needs. Demand for AI compute is exploding, but the supply is struggling to keep up. Our current mechanisms for training AI systems utilise a narrow set of algorithms and hardware building blocks which require significant capital to develop and produce. By contrast, natural processing systems innately process complex information more efficiently – on several orders of magnitude. Through our programme, Scaling Compute, we’re looking to uncover new technological pathways that can bridge this gap and bring the cost of AI hardware down by >1000x. We’re funding 12 teams of Creators in a coordinated R&D effort, spanning academia, non-profit R&D organisations, startups and multinational companies. Our Creators bring together the expertise, capital and networks required to pull new ideas into prototypes, and onward to real-world applications. Swipe to discover our approach, and meet the teams here: https://lnkd.in/egfcW5Ap