Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Field
-
. Advanced FIB-SEM facilities are available at Utrecht University’s Electron Microscopy Center. The project further benefits from excellent dedicated CPU and GPU computing infrastructure to support large-scale
-
following technology areas: hardware/software co-design, performance optimization with heterogeneous and alternative computing systems (CPU/GPU/NPU/etc.), FPGA design, high-performance computing (HPC
-
scientists and engineers are accustomed to. Moreover, the vast majority of the performance associated with these reduced precision formats resides on special hardware units such as tensor cores on NVIDIA GPUs
-
(PyTorch, TensorFlow). Experience with dataset curation, annotation workflows, FAISS/embedding retrieval, LLM-based parsing, RAG-style pipeline, and GPU/HPC training. Familiarity with 3D data processing
-
projects at CASS. The center fellows will have access to a 70,000-core Infiniband Cluster (Jubail) dedicated to the science division, several GPU-based clusters at NYUAD, and other supercomputer facilities
-
with edge computing or embedded systems (e.g., NVIDIA Jetson, Raspberry Pi) Background in real-time processing and GPU acceleration (CUDA) Participation in relevant competitions (e.g., Kaggle, computer
-
GPU utilization and allocate computing resources efficiently across users. c) create and manage user accounts for faculty and students; troubleshoot user issues; and design and deliver
-
University of New Hampshire – Main Campus | New Boston, New Hampshire | United States | about 1 month ago
. The researcher will be provided access to state-of-the-art supercomputing facilities with advanced GPU and data storage capabilities. Additionally, opportunities will be available for collaborations
-
of today’s heterogeneous hardware (multicore CPUs, GPUs, SmartNICs, disaggregated datacenters). We explore: SmartNICs & P4 switches for offloading intelligence from hosts Device-to-device communication
-
linear algebra computations, building software for scientific applications using GPUs (Graphics Processing Unit), multi-threading and parallelism, numerical discretization methods (finite differences