Pytorch Engineer

As a PyTorch Engineer at Graphcore, you will be integral to the Frameworks team, focusing on enhancing the compatibility and performance of Graphcore's machine learning accelerators with leading frameworks like PyTorch and Triton. This role involves close collaboration with a diverse group of engineers dedicated to advancing artificial intelligence compute solutions.

Your primary responsibilities will include designing and implementing new features, maintaining and supporting existing functionalities, and developing comprehensive tests to ensure software reliability. You will also be tasked with optimizing the software stack for improved performance, managing complex technical tasks with cross-team dependencies, and contributing to technical documentation and user manuals.

The ideal candidate will possess strong software engineering skills, with experience in Python development and the creation of performant C++ applications in a commercial setting. Additionally, expertise in at least one of the following areas is required: writing machine learning kernels, compiler development, utilization or development of machine learning frameworks, or experience in a computationally intensive engineering field.

Graphcore offers a competitive salary along with flexible working arrangements, a generous annual leave policy, private medical insurance, a health cash plan, a dental plan, pension matching up to 5%, life assurance, and income protection. Additional benefits include a generous parental leave policy, an employee assistance program, and a well-stocked central Bristol office featuring a barista bar.

Joining Graphcore means becoming part of a culture that values continuous learning and innovation. The company fosters an inclusive environment where diverse backgrounds and perspectives are embraced, providing ample opportunities for professional growth and development in the rapidly evolving field of artificial intelligence.