Our research group currently has 3 open PhD vacancies. Click on the positions to get more details about the research involved and how to apply.
- Position 1: Power consumption versus performance trade-offs for GPUs and emerging hardware architectures (deadline mid-December, 2025)
This PhD project is focused on exploring how to balance power consumption and performance for AI inference on hardware accelerators like GPUs (and emerging architectures). The goal is to develop techniques that make computation more energy efficient by using both compile time strategies (analyzing code to pick energy aware execution plans) and run time optimization (dynamically choosing low-power modes based on workload and data). The research is validated on edge GPUs and simulated future 3D architectures, aiming to enable more efficient AI execution across current and next-generation hardware. - Position 2: AI-assisted High-Framerate Speckle Image Analysis (deadline mid-December, 2025)
This PhD position at imec aims to translate High Framerate Speckle Imaging (HFSI) into clinical use by combining ultra-fast speckle video acquisition (3,000 fps in full HD) with AI driven image analysis. Unlike standard photoplethysmography (PPG), this speckle-based method is more robust to skin pigmentation and ambient light, and with high temporal and spatial resolution it can separate vessel wall motion, blood flow, and tissue viscoelasticity, as well as estimate oxygenation. The candidate will design optimized HFSI setups for surgical contexts (e.g., laparoscopic surgery), create AI models for tissue segmentation, classification, and perfusion measurement, and validate the system in phantoms, animal models, and clinical settings — all while overcoming challenges of low signal to noise ratios and high data rates (~1 GB/s) - Position 3: Advancing outdoor hyperspectral imaging under challenging illumination conditions (deadline mid-December, 2025)
This PhD project aims to make hyperspectral imaging more reliable and interpretable in real world outdoor settings (e.g., agriculture, infrastructure, automotive) by tackling issues like changing solar radiation, viewing angles and complex scene geometry. To do this, the researcher will develop methods such as multi exposure acquisition or adaptive sensing, sensor fusion, build new data representations (extending BRDF models), correct for radiance variability, and explore machine learning techniques using reference objects with known spectra to compensate for lighting and angle effects. The project combines modeling, sensor design, and ML to dramatically improve data trustworthiness in outdoor hyperspectral imaging and gives the student hands on experience with state of the art imec hyperspectral technology.
We offer you the opportunity to do full-time research in a highly international and friendly working environment, with a competitive salary at Ghent University, in the context of an interdisciplinary research project. As a researcher within imec-IPI, you will publish your research results at major international conferences and in scientific journals in order to pursue your PhD degree. You will also assist in limited educational tasks of the research group. IPI provides ample opportunity for researchers to take initiative in their work and to develop their professional networks.
Image Processing and Interpretation (IPI) is an imec research group at Ghent University. IPI consists of 40 researchers and conducts state of the art research in the field of digital image and video processing for a wide range of applications including real-time image and video processing, and machine learning, covering a wide range of application domains, including industrial inspection, (ultra) high-definition video improvement, smart multi-camera networks, mobile mapping, real-time vision and sensor fusion, and medical imaging.
Ghent University consistently ranks among the best 100 universities in the world, including, 69th by the Academic Ranking of World Universities (or Shanghai ranking) and 88th by U.S. News & World Report. The IPI Lab is location on the university’s UFO campus in the center of Ghent, Belgium, a city recently rated as one of the best places to visit in Europe for culture.
