Graduate Performance Engineer

About the role

Graphcore is a global leader in artificial intelligence computing systems. We design advanced semiconductors and data center hardware that deliver the specialized processing power needed to advance AI while improving the efficiency required for broad adoption. As part of SoftBank Group, Graphcore belongs to a family of companies developing some of the world’s most transformative technologies. Our new AI Engineering Campus in Austin will play a central role in building the future of AI computing.

The Opportunity As a Graduate Performance Engineer, you will contribute to the design, integration, bring-up, and validation of complex server- and rack-level performance of elaborate, large-scale systems. You will work alongside experienced engineers, software developer, and cross-functional partners while building practical skills in component, system and scale up/out performance optimization and design.

Responsibilities

• Support the design, peer review, bring-up, and debug of complex server- and rack-level systems.
• Assist with modeling, design and evaluation of the complete software and hardware stack identifying performance bottlenecks, possible solutions and testing those outcomes.
• Collaborate with many different teams across both hardware and software development and testing.

Requirements

• A bachelor’s or master’s degree in electrical engineering, computer engineering, or a related discipline, completed before the role’s start date. Equivalent relevant education or practical experience will also be considered.
• Foundational knowledge of software development, hardware architecture and general understanding of performance implications.
• Hands-on experience gained through coursework, laboratories, internships, research, student projects, or personal projects.
• Ability to analyze technical problems, document your work, communicate clearly, and collaborate effectively.
• Curiosity, sound engineering judgment, and a willingness to learn in a fast-moving, multidisciplinary environment.

Preferred Qualifications

• Software and hardware architecture especially focused on performance implications
• Familiarity with high-speed interfaces such as PCI Express (PCIe), DDR memory, or Ethernet.