About Us

Graphcore is a globally recognised leader in Artificial Intelligence computing systems. The company designs advanced semiconductors and data centre hardware that provide the specialised processing power needed to drive AI innovation, while delivering the efficiency required to support its broader adoption.

As part of the SoftBank Group, Graphcore is a member of an elite family of companies responsible for some of the world’s most transformative technologies. We are opening a new AI Engineering Campus in Austin, which will play a central role in Graphcore's work building the future of AI computing.

Role Overview

We are seeking a highly skilled and motivated Systems Engineer with a niche focus on network interconnects within blade and rack-level systems. This role is pivotal in designing, analyzing, and optimizing the physical and logical interconnection of compute, storage, and accelerator components in high-performance systems! The ideal candidate will possess deep expertise in networking standards, topologies, and technologies used in datacenters, HPC systems, and cloud-scale infrastructure.

Key Responsibilities

Architecture and Design:

• Define and architect rack-level network topologies (e.g., 200/400/800G Ethernet, Smart NICs, Network Security, etc.) for scalable system designs.

• Collaborate with hardware and software engineering teams to design network interconnect solutions aligned with performance, power, and cost goals within the rack.

• Evaluate and select network fabrics (e.g., Ethernet, InfiniBand, CXL, PCIe) based on system requirements.

• Extensive knowledge on specifying, designing Scale-Up and Scale-Out Network Topologies.

Performance and Simulation:

• Model and simulate network performance across rack-level systems.

• Perform bottleneck analysis and propose optimizations for bandwidth, latency, and reliability.

Integration and Validation:

• Collaborate with platform and board teams to ensure seamless integration of interconnects at the physical and logical levels.

• Define test plans and support bring-up and validation of networking subsystems.

• You'll work with Industry Network vendors to ensure solutions meet the technical requirements and features required for AI/ML systems.

Standards and Compliance:

• Maintain awareness of evolving standards (e.g., IEEE 802.3, OCP NIC, OSFP, QSFP-DD) and contribute to the development of internal guidelines.

• Ensure systems meet regulatory and industry compliance for networking hardware.

Cross-Functional Collaboration:

• Partner with software, firmware, and datacenter infrastructure teams to ensure end-to-end functionality and compatibility.

• Work with vendors and technology partners for roadmap alignment and issue resolution.

• Work closely with ODM partners to ensure integration and test requirements are developed and ensure proper validation coverage.

Qualifications:

Required:

• Bachelor’s or Master’s degree in Electrical Engineering, Computer Engineering, or related field with 5+ years of experience in systems or network engineering, preferably in datacenter or HPC environments.

• Strong understanding of rack-level network topologies and high-speed interconnect technologies.

• Hands-on experience with Ethernet and/or InfiniBand networking, including QSFP/OSFP modules and switching.

• Familiarity with Layer 1–3 networking protocols and performance tuning.

• Experience with simulation tools and methodologies for network performance analysis.

Preferred:

• Knowledge of CXL, NVLink, or PCIe-based interconnects.

• Experience with Open Compute Project (OCP) hardware and standards.

• Experience in thermal and power modeling related to networking hardware.

• Scripting skills (Python, Bash) for automation and analysis.

Benefits

In addition to a competitive salary, Graphcore offers a competitive benefits package. We welcome people of different backgrounds and experiences; we’re committed to building an inclusive work environment that makes Graphcore a great home for everyone. We offer an equal opportunity process and understand that there are visible and invisible differences in all of us. We can provide a flexible approach to interview and encourage you to chat to us if you require any reasonable adjustments.