Sort by
Refine Your Search
-
Listed
-
Category
-
Field
-
learning algorithms for engineering systems Programming experience in FORTRAN, C, or C++ and scripting experience in Python or similar languages Experience with parallel computing environments and Linux
-
environments Experience with parallel computing environments, HPC in a Linux environment Experience with surrogate modeling Experience with data analytics techniques Familiarity with C++ and GPU programming
-
environments Experience with parallel computing environments, HPC in a Linux environment Experience with surrogate modeling Experience with data analytics techniques Familiarity with C++ and GPU programming
-
diagnostics. Experience with Infiniband networks and diagnostics. Extensive experience with High Performance Parallel File Systems (Lustre, WEKA, GPFS, etc). Experience with performance and diagnostic tools
-
Leadership, Coordination, and Platform Stewardship Serve as the primary technical liaison between hardware developers, software engineers, data scientists, and scientific users. Coordinate parallel development
-
Lustre parallel file system. NCCS serves multiple agencies including DOE, NOAA, and the Air Force. The NCCS also supports the center’s Quantum Computing User Program (QCUP) which provides access to state
-
Theoretical Physics or a related discipline completed within the last 5 years. Experience with High Performance Computing and programming for massively parallel computers. Experience with quantum many-body
-
systems. Expertise with batch schedulers (SLURM, PBS, LSF) and parallel file systems (Lustre, GPFS/Spectrum Scale). Proven ability to lead technical projects from concept through implementation, balancing
-
for massively parallel computers. Experience with quantum many-body methods. Preferred Qualifications: A strong computational science background. Familiarity with coupled-cluster method. Understanding
-
for Science @ Scale: Pretraining, instruction tuning, continued pretraining, Mixture-of-Experts; distributed training/inference (FSDP, DeepSpeed, Megatron-LM, tensor/sequence parallelism); scalable evaluation