Skip to main content

Graphcore

Graduate Performance Engineer

Austin, Texas, United StatesentryAdded today

About this role

Graphcore seeks a recent graduate to support the design and validation of high-performance server and rack-level AI computing systems. You'll collaborate with hardware and software teams to optimize complex systems, identify performance bottlenecks, and contribute to bringing up large-scale infrastructure in our Austin engineering campus.

What you'll do

  • Support design, peer review, bring-up, and debugging of complex server and rack-level systems
  • Model and evaluate complete software and hardware stacks to identify performance bottlenecks
  • Develop and test solutions for performance optimization across components and systems
  • Collaborate with hardware and software development teams on cross-functional initiatives
  • Document technical work and communicate findings clearly to engineering teams
  • Assist with system validation and performance testing at scale

What they're looking for

  • Software development fundamentals
  • Hardware architecture understanding
  • Performance analysis and optimization
  • System-level debugging
  • Technical documentation and communication
  • PCIe, DDR memory, or Ethernet protocols (preferred)
  • Problem-solving and analytical thinking
  • Hands-on lab and experimental experience
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Graphcore

Graphcore builds advanced AI compute silicon and systems designed for high-performance machine learning applications. The company is hiring Systems Engineers, Validation Engineers, and Electrical Engineers to develop and validate innovative hardware platforms, from PCB design through production deployment.

View all jobs at Graphcore

Likely interview questions

  • Describe a complex technical project from your coursework or internship where you identified and resolved a performance bottleneck.
  • How would you approach debugging performance issues in a large-scale server system you're unfamiliar with?