Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Employer
- Nature Careers
- Oak Ridge National Laboratory
- Carnegie Mellon University
- Forschungszentrum Jülich
- Nanyang Technological University
- University of California Davis
- University of Texas at Dallas
- University of Toronto
- Argonne
- Fraunhofer-Gesellschaft
- Technical University of Munich
- University of Dayton
- University of North Carolina at Chapel Hill
- ;
- California Institute of Technology
- Central China Normal University
- Cold Spring Harbor Laboratory
- Durham University
- ETH Zurich
- Empa
- Free University of Berlin
- IMEC
- Imperial College London;
- Inria, the French national research institute for the digital sciences
- Johns Hopkins University
- KINGS COLLEGE LONDON
- KU LEUVEN
- King Abdullah University of Science and Technology
- London School of Economics and Political Science;
- Los Alamos National Laboratory
- Medical Research Council
- NTNU - Norwegian University of Science and Technology
- Northeastern University
- Purdue University
- Rutgers University
- Technical University of Denmark
- Temple University
- The Chinese University of Hong Kong
- The Ohio State University
- The University of Edinburgh;
- University of Arkansas
- University of Birmingham
- University of California
- University of California Berkeley
- University of Delaware
- University of Florida
- University of Glasgow
- University of Illinois at Urbana Champaign
- University of Maryland, Baltimore County
- University of Minnesota
- University of North Texas at Dallas
- University of Oxford
- University of Pittsburgh
- University of Trento
- University of Washington
- Washington University in St. Louis
- 46 more »
- « less
-
Field
-
efficiency for serving massive models. Research and implement cutting-edge optimization strategies at the kernel level (e.g., FlashAttention, custom CUDA/ROCm kernels). Build robust data pipelines
-
University of North Carolina at Chapel Hill | Chapel Hill, North Carolina | United States | 4 days ago
). Experience and proficiency across the software development lifecycle (version control, documentation, and testing) is required. Experience with GPU acceleration frameworks (Nvidia CUDA, PyCUDA, CuPy
-
using the shared memory and message passing techniques. Knowledge of OpenMP and MPI or similar programming directives and libraries. Knowledge of GPU programming with CUDA, HIP, oneAPI or OpenMP for GPUs
-
with job schedulers, e.g. SLURM, PBS, SGE, etc. ● Experience working at an academic institution ● Experience with parallel codes and libraries (e.g. MPI, OpenMP, Cuda) ● Experience with research and/or
-
languages used: C++ 2014, CUDA, Lua Desirable: - interest in high-performance computing with graphics processors (GPUs) and simulation methods - fluent knowledge of modern C++ and a scripting language
-
scripting methods (i.e. Python, MATLAB, C++, CUDA, Bash, and/or SQL) and machine learning / deep learning methods Active learning, exploration, optimal experiment design, Bayesian optimization, reinforcement
-
, CUDA) and good understanding of hardware used in large scale HPC clusters such as hybrid CPU+GPU systems, memory hierarchies and file systems; experience with job schedulers (e.g., Slurm, FLUX) and
-
mathematics, e.g., probability theory, linear algebra, differential/integral calculus Prior programming experience in Python is a must, C++ and CUDA experience are a plus Hands-on experience in working with
-
performance computing using SLURM or LSF Experience with PyTorch, JAX, or Tensorflow Experience with NVIDIA CUDA and related OpenMP programming Experience with cloud services (AWS, GCP, Azure, etc) Experience
-
and train CNN and SNN models utilizing frameworks such as Keras, PyTorch, and SNNtorch Implement GPU acceleration through CUDA to enable efficient neural network training Apply hardware-aware design