Duration: Fully funded for 1-year with a possibility of extension of one year.
Country/Territory: Italy
Organization: University of Trento
More information: Link
Contact: Kasim Sinan Yildirim <kasimsinan.yildirim@unitn.it>
One postdoc position on machine learning on embedded systems will be opening soon as a part of GEMINI (“Green Machine Learning for the IoT”) national research project funded by the Italian MUR under the PRIN at the University of Trento, Italy.
The position is initially fully funded for 1-year with a possibility of extension of one year.
The goal of the GEMINI project is to design and implement a novel framework to support the development of green and even fully sustainable TinyML applications distributed in an edge-to-cloud continuum. The framework will support batteryless embedded devices, also the ones without network connectivity. GEMINI aims at providing the following building blocks:
- efficient data collection, ML model generation, compression, and code generation for memory-constrained IoT devices;
- zero-power deployment of the models via novel communication protocols exploiting backscatter and visible light communication;
- intermittent execution and acceleration of the trained ML model on the batteryless edge by relying only on energy harvesting.
The research will be intersecting with the following topics:
Energy Efficient and Low-Power Computing
Intermittent Computing and Batteryless Systems
Machine Learning on Microcontrollers (Tiny Machine Learning)
Embedded Systems and Software Support
Architectural and Hardware Support
The starting date for the postdoc can be negotiated (preferably as soon as possible).