maintainable solutions. PREFERRED EXPERIENCE: GPU Kernel Development & Optimization: Proficient experienced in designing and optimizing GPU kernels for deep learning on AMD GPUs using HIP, CUDA, and assembly (ASM). Strong knowledge of AMD architectures (GCN, RDNA) and low-level programming to maximize performance for AI operations, leveraging tools like More ❯
different compute, memory and communication configurations for Ai acceleration. What's required for this HPC Software Engineer position? Strong C/C++ Development Extensive CUDA/OpenCL/MPI experience Experience with GPU acceleration Experience with Ai/ML inference frameworks Experience in analysing workload sensitivity If you are More ❯
different compute, memory and communication configurations for Ai acceleration. What's required for this HPC Software Engineer position? Strong C/C++ Development Extensive CUDA/OpenCL/MPI experience Experience with GPU acceleration Experience with Ai/ML inference frameworks Experience in analysing workload sensitivity If you are More ❯
maintainable solutions. PREFERRED EXPERIENCE: GPU Kernel Development & Optimization: Proficient experienced in designing and optimizing GPU kernels for deep learning on AMD GPUs using HIP, CUDA, and assembly (ASM). Strong knowledge of AMD architectures (GCN, RDNA) and low-level programming to maximize performance for AI operations, leveraging tools like More ❯
days a week in the Cambridge office. This role focuses on maintaining and optimising the Linux operating system, file systems, and software stack (Cuda, PyTorch, Python etc) for machine learning projects as well as setting up and configuring NVIDIA HGX servers (installing and updating software, managing user access, and More ❯
for QEMU and DynamoRIO (or x86 PIN). Experience in developing and using performance simulators like GEM5 (O3 model), Sniper or others Experience with CUDA or OpenCL programming is a plus More ❯
for QEMU and DynamoRIO (or x86 PIN). Experience in developing and using performance simulators like GEM5 (O3 model), Sniper or others Experience with CUDA or OpenCL programming is a plus More ❯
for QEMU and DynamoRIO (or x86 PIN). Experience in developing and using performance simulators like GEM5 (O3 model), Sniper or others Experience with CUDA or OpenCL programming is a plus More ❯
