We’re delighted to announce that the flagship project DOMINO has been selected for funding by the Austrian Research Promotion Agency (FFG)!

Led by TU Wien, the consortium brings together leading experts from industry and academia, with Daniel Müller-Gritschneder as one of the project leads. The project was selected for funding in FFG’s AI Ecosystems 2024: AI for Tech, AI for Green and AIM AT call, awarded over €2,4 Million, and is set to run until April 2028.

ML DevOps Methods for a Green and Safe EdgeAI Lifecycle (DOMINO) investigates Edge computing, and particularly Edge AI. Edge computing offers major advantages over cloud-based solutions in terms of latency, privacy, safety, cost, and energy efficiency, and is rapidly gaining market relevance. While mature platforms exist for deploying AI on edge devices, they largely focus on initial deployment and fall short of addressing the full lifecycle and the stringent requirements of industrial and safety-critical applications. DOMINO addresses this gap by developing an end-to-end MLOps lifecycle for Edge AI, inspired by DevOps, covering development, deployment, monitoring, evaluation, and continuous improvement. It specifically targets industrial integration, compliance with safety norms and the EU AI Act, lifecycle monitoring, and the use of non-expert feedback to improve deployed systems without degradation. Daniel’s work within the consortium focuses on hardware-aware Neural Architecture Search (NAS) to identify efficient vision models for railway and industrial applications. NAS automates the design of neural networks tailored to diverse Edge AI platforms, taking into account specialized compute units such as NPUs and GPUs, as well as memory constraints.

FFG flagship projects (“Leitprojekte”) are strategically conceived, large-scale research and development initiatives. They are designed to integrate the entire value chain and to demonstrate the technological feasibility of system-level solutions with long-term growth potential. These projects strengthen specific sectors or industries while developing model solutions to major societal challenges.

About

Daniel Müller-Gritschneder is a Professor of Computer Architecture and Head of the Research Unit Embedded Computing Systems at TU Wien Informatics. He received his Diploma, doctoral, and habilitation degrees in electrical engineering and information technology from the Technical University of Munich, where he was also a researcher at the Chair of Electronic Design Automation from 2004 to 2024. He worked on several projects in close cooperation with industry partners such as Infineon, Intel, Siemens, and Bosch. He serves as a TPC member at EDA conferences such as DAC, ICCAD, SAMOS, and CODES/ISSS, and was co-organizer of the RISC-V Summit Europe 23 and 24. He is also a senior member of IEEE. His main interests are in Electronic System Level Design, RISC-V, tinyML, as well as functional safety and HW security.

Curious about our other news? Subscribe to our news feed, calendar, or newsletter, or follow us on social media.