7 of 7 Permanent OpenCL Jobs in London

memory, bandwidth, power/thermal, or cost). Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL, MLIR, ONNX) and confidence learning adjacent frameworks quickly. Comfort operating at multiple levels of abstraction — from high-level model behaviour down to low-level ...

latency, memory, bandwidth, power/thermal, or cost).Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL, MLIR, ONNX) and confidence learning adjacent frameworks quickly.Comfort operating at multiple levels of abstraction — from high-level model behaviour down to low-level kernel ...

latency, memory, bandwidth, power/thermal, or cost).Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL) and confidence learning adjacent frameworks quickly.Comfort operating at multiple levels of abstraction — from high-level model behaviour down to low-level kernel/runtime ...

PyTorch (not just using high-level tooling).Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL) and confidence learning adjacent frameworks quickly.Comfort operating at multiple levels of abstraction — from high-level model behaviour down to low-level kernel/runtime execution.Familiarity ...

PyTorch (not just using high‐level tooling). Strong proficiency with at least one relevant stack/toolchain (e.g. TensorRT, CUDA, Qualcomm QNN, Triton, OpenCL) and confidence learning adjacent frameworks quickly. Comfort operating at multiple levels of abstraction — from high-level model behaviour down to low-level kernel/ ...

Developers MUST have: (the below also gives you an idea of stack)C++ 11Computer Science DegreeSingle Core and Distributed C++C++ Shared LibrariesVersion ControlIdeally OpenMP, OpenCL or TBBThe environment is that of Facebook or Google, relaxed open with time to think and make the right decisions. The atmosphere is calm ...

strong focus on memory management, multi-threading, and low-level performance optimizations Experience with GPU architectures (e.g., NVIDIA, AMD) and programming frameworks like CUDA, OpenCL, and TensorFlow Understanding of machine learning algorithms, including model training and inference, and how to optimize these for GPU-based computation Strong knowledge ...