CUDA/OpenCl Kernal Engineer

CUDA/OpenCL Kernal Engineer Contract

6 month Initial Term - Outside IR35 - Hybrid (Cambridge)

Role:

As a CUDA/OpenCL Kernel Developer, you will play a critical role in designing, optimising, and implementing kernels for hardware accelerators such as GPUs.

You will collaborate closely with hardware and software teams to ensure that accelerators deliver optimal performance and efficiency across a wide range of applications. This role requires strong expertise in CUDA/OpenCL Kernel Development and a deep understanding of hardware architecture.

Responsibilities:

Design and develop high-performance CUDA kernels for neural network inference, training, or other compute-intensive tasks. Optimise existing CUDA kernels to improve performance, reduce latency, and minimise power consumption

What we need:
Strong proficiency in CUDA, OpenCL programming and GPU architecture Strong experience in Kernal development for GPU's or similar Familiarity with machine learning frameworks such as TensorFlow, PyTorch, or CUDA-based libraries like cuDNN is a plus.