Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Program
-
Field
-
Proficiency in CUDA programming and hardware-accelerated computing Experience with high-performance I/O and efficient data access protocols for distributed scientific computing Expertise in customizing data
-
– Fellowship application (https://drh.tecnico.ulisboa.pt/bolseiros/recrutamento/ ); ii) Curriculum Vitae; iii) academic degree certificate; iv) motivation letter. Applications must be submitted to the email
-
-node, or GPU-accelerated execution. Expertise with HPC and AI software stacks including MPI, CUDA, OpenMP, ROCm, AI/ML frameworks, and distributed computing libraries (Dask, Ray, Horovod). Strong
-
programming paradigms and frameworks like MPI (Message Passing Interface), OpenMP, CUDA, or OpenACC for developing highly parallelized applications. Familiarity with HPC tools and libraries such as SLURM, PBS
-
modelling is an advantage. Programming skills (e.g., C++, Python, CUDA) and familiarity with high-performance computing are considered assets. You are enthusiastic, self-motivated, and capable
-
computer architecture Parallel programming of HPC/AI accelerators (CUDA, OpenMP, SYCL, etc.) Salary Gross annual: €39,224 Application Deadline 07 October 2025, 12:00 (CET) via University of Trento
-
and distributed systems, for example using programming models like OpenMP, CUDA, SYCL, and MPI. Experience with distributed software development workflows (e.g., Git, code review, unit testing, CI/CD
-
Operating System (ROS/ROS2). Solid experience with computer vision libraries (OpenCV) and deep learning frameworks (PyTorch, CUDA) A firm grasp of control theory and its practical application in robotic
-
. Knowledge of systems programming skills and concepts Experience with fundamental OS and storage concepts. Experience with programming heterogenous architecture. Preferred Qualifications: Experience with CUDA
-
Mathematics at the Technical University of Munich (TUM) invites applications for one PhD position. The student will work on developing scalable distributed preconditioners in Ginkgo (https://github.com/ginkgo