Sort by
Refine Your Search
-
Listed
-
Category
-
Employer
- Delft University of Technology (TU Delft)
- Delft University of Technology (TU Delft); 16 Oct ’25 published
- Delft University of Technology (TU Delft); Published yesterday
- Erasmus MC (University Medical Center Rotterdam); Rotterdam
- Radboud University
- University of Amsterdam (UvA)
- University of Amsterdam (UvA); Published today
- Vrije Universiteit Amsterdam
- Vrije Universiteit Amsterdam (VU)
-
Field
-
FPGAs, CGRAs, and many Machine Learning accelerators, offer significant opportunities for improving performance and energy efficiency compared to traditional CPUs/GPUs. Yet, porting and optimizing code
-
FPGAs, CGRAs, and many Machine Learning accelerators, offer significant opportunities for improving performance and energy efficiency compared to traditional CPUs/GPUs. Yet, porting and optimizing code
-
segmentation." CVPR. 2022. [3] van Spengler, Max, and Pascal Mettes. "Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space." ICML. 2025. [4] Pal, Avik, Max van Spengler, Guido Maria D'Amely di
-
, and supportive atmosphere, equipped with state-of-the-art research facilities, including dedicated GPU clusters, data servers, and personal GPU-enabled workstations. You will join a multidisciplinary
-
background in machine learning, deep learning, and/or computer vision; Experience in programming. Python is a must, lower-level GPU programming experience is a bonus; Strong grasp on the English language
-
in high-performance computing using MPI. Experience in GPU programming using OpenACC, CUDA, CUDA-Fortran, Julia, or related tools. Experience in CFD meshing software. TU Delft (Delft University
-
recommended. Other valuable skills include: Experience in high-performance computing using MPI. Experience in GPU programming using OpenACC, CUDA, CUDA-Fortran, Julia, or related tools. Experience in CFD
-
6G testbeds (indoor and outdoor) with GPU clusters and edge computing platforms Global Internet measurement infrastructure and satellite network access Opportunities to engage with Internet
-
, which has multiple test machines with GPUs and AI accelerators. The algorithms used can be bound by the available compute power or memory bandwidth in different parts of the program. This information will