POSTDOC POSITION ON NONLINEAR PROCESSING UNITS FOR CMOS-COMPATIBLE BRAIN-INSPIRED COMPUTING

Are you interested in a job at the interface of electrical engineering and device physics to contribute to a new generation of energy-efficient hardware for artificial intelligence? If you have a PhD with background in microelectronics, computer architecture or hardware for machine learning, you may want to apply for this PostDoc position within the dynamic Horizon Europe Pathfinder project HYBRAIN.

This position is part of the Horizon Europe Pathfinder project HYBRAIN, coordinated by the University of Twente and in collaboration with IBM Zürich and the universities of Oxford and Heidelberg. HYBRAIN’s vision is to realise a radically new technology for ultra-fast and energy-efficient edge AI inference based on a world-first, unique, brain-inspired hybrid architecture of integrated photonics and unconventional electronics with collocated memory and processing. As the most stringent latency bottleneck in CNNs arises from the initial convolution layers, we will take advantage of the ultrahigh throughput and low latency of photonic convolutional processors (PCPs). Their output is processed using cascaded analog electronic linear and novel nonlinear classifier layers.

In 2020 we introduced the concept of dopant network processing units (DNPUs, Nature 577, 341-345 (2020). In this postdoc project, you will work on the development of efficient (CMOS-based) electronics and machine-learning procedures to be applied in hybrid architectures of DNPU networks, integrated photonics and analog in-memory computing.