Sort by
Refine Your Search
-
current practice). Demonstrated expertise in AI/ML. Proven track record in application performance optimization. Advanced experience with parallel programming models (e.g., OpenMP, MPI, CUDA). Extensive
-
researchers to integrate computing techniques into research activities using common HPC programming languages, tools, and techniques including Fortran and/or C/C++, MPI, OpenMP, CUDA An equivalent combination
-
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 | 2 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
-
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
-
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
-
, 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