Compute Library Engineer

Description:

I'm currently working with a Cambridge-based, multinational Semiconductor scale-up who are focused on developing AI accelerators. You will have the opportunity to work in a rapidly changing environment where your new ideas will become innovative products, services, and customer experiences. They are a successful, growing business, offering the chance for an engineer to progress their career and achieve future aspirations. They provide a stable and supportive environment.

They are looking for a Compute Library Engineer to develop and optimise high-performance kernels for ML operators on NPU architectures. They are looking for an exceptional engineer to join a talented team of 5 engineers at an exciting time of growth for the company. You will have had some experience in the mentorship of more junior engineers and you will be utilising hardware features of GPU and accelerators specialised for Ai applications. You will also collaborate with the hardware and software teams to integrate kernels into the NPU framework.

What's required for a successful Compute Library Engineer?

• Extensive experience in kernel development projects for GPUs
• Involvement in OpenCL, CUDA or similar parallel programming languages
• Understanding of ML frameworks - TensorFlow, PyTorch etc
• Strong C++ development skills
• Ability to work independently in a fast-paced environment