Jobs at Graphcore

Provides advanced troubleshooting, bring-up, validation, and reliability support for AI compute hardware across lab and data center environments. Diagnoses server, motherboard, power, thermal, network, BIOS, and BMC issues; performs root cause analysis; supports deployment qualification; develops SOPs and validation documentation; collaborates with engineering and infrastructure teams; and mentors junior staff. The role may include on-call support during hardware milestones.

Develop system-level diagnostics and stress-testing software for next-generation AI silicon. Build configurable validation tools that detect data corruption, hardware instability, timing issues, and performance or reliability problems across CPUs, accelerators, memory, PCIe, firmware, and other platform components. Collaborate with hardware, firmware, and validation teams to improve observability, fault isolation, silicon bring-up, and platform reliability.

Develop and extend system-level diagnostics, stress-testing software, and validation tools for next-generation AI SoCs. The role focuses on detecting hardware failures, silent data corruption, timing issues, and reliability problems across CPUs, accelerators, memory, PCIe, storage, firmware, BMC, and operating systems. Responsibilities include integrating Arm diagnostics, automating validation across server and rack-scale platforms, debugging hardware-software interactions, improving observability and fault isolation, and collaborating with hardware, firmware, and validation teams.

Develop system-level diagnostic and stress-testing software for next-generation AI SoCs. Build reusable validation utilities for CPUs, memory, interconnects, PCIe, storage, firmware, and platform components. Investigate silent data corruption, timing issues, hardware instability, and cross-layer failures across multiple platforms and silicon revisions. Collaborate with hardware, firmware, software, and validation teams to improve observability, fault isolation, silicon bring-up, and platform reliability.

Develop and maintain PCB component libraries, footprints, symbols, 3D models, and multilayer board layouts using Cadence Allegro/OrCAD. Validate component data, perform placement and routing, run design rule checks, and prepare fabrication and assembly deliverables. Collaborate with electrical, mechanical, manufacturing, procurement, and suppliers to resolve design issues, support engineering changes, ensure design-for-manufacturability, and maintain accurate release documentation.

Supports the design, integration, validation, and performance analysis of advanced AI computing platforms. Responsibilities include developing validation plans and automation scripts, conducting laboratory measurements, analyzing performance and power data, troubleshooting system issues, investigating root causes, and documenting technical results. The engineer collaborates with hardware, firmware, software, mechanical, thermal, manufacturing, and systems teams throughout the development lifecycle.

Design and validate mechanical and thermal components for advanced AI hardware and data center systems. Create CAD models and drawings, develop and execute prototype tests, analyze data, troubleshoot issues, support verification, and document engineering results. Collaborate with thermal, electrical, hardware, systems, and manufacturing teams throughout the product development lifecycle.

Develop and validate low-level embedded firmware for advanced compute systems. Responsibilities include firmware implementation, automated testing, Linux-based debugging, hardware bring-up, lab validation, continuous integration, root-cause analysis, and collaboration across hardware, silicon, systems, and software teams. The role also involves documenting designs and test findings, conducting engineering experiments, and supporting reliable firmware delivery.

Supports post-silicon validation of AI server blades and racks through testcase planning, automation, execution, system provisioning, failure triage, debugging, coverage tracking, and root-cause analysis. Collaborates with silicon, firmware, systems, and platform teams to validate CPU/GPU, memory, I/O, BIOS, BMC, operating system, and rack-level functionality and performance.

Support hardware platform design, laboratory testing, system validation, automation, and performance analysis for advanced AI compute systems. Develop scripts, analyze power and signal measurements, investigate issues, and collaborate across hardware, firmware, software, mechanical, thermal, and systems teams. Candidates should be enrolled in a relevant degree program and have lab-testing experience, programming or scripting knowledge, and foundational computer architecture or embedded-systems understanding.

Supports the design, integration, bring-up, debugging, and validation of server- and rack-level performance. Analyzes hardware and software architectures to identify bottlenecks, evaluates optimization approaches, and collaborates with cross-functional engineering and testing teams.

Mechanical Engineering Intern supporting mechanical design and thermal validation of AI hardware. Responsibilities include 3D CAD modeling, assemblies and drawings, laboratory setup, thermal and mechanical testing, data analysis, prototype evaluation, troubleshooting, design verification, documentation, and cross-functional collaboration.

Firmware Engineering Interns contribute to embedded and system firmware development, testing, debugging, automation, and hardware bring-up in a Linux environment. Responsibilities include writing C, C++, or Python code, creating automated tests, conducting engineering experiments, supporting CI/CD workflows, diagnosing hardware-software interactions, documenting findings, and collaborating with firmware, hardware, silicon, systems, and software teams.

Provides advanced hardware support for Arm-based AI compute platforms across lab and data center environments. Leads troubleshooting, hardware bring-up, component validation, firmware interaction testing, system failure diagnosis, root cause analysis, qualification, and deployment. Develops troubleshooting documentation, collaborates with engineering and infrastructure teams, mentors junior staff, and participates in on-call support during critical hardware milestones.

Provides advanced operational, diagnostic, and engineering support for Arm-based AI hardware platforms across lab and data center environments. Leads hardware bring-up, validation, break-fix troubleshooting, root cause analysis, and qualification for server blades, racks, power systems, and infrastructure. Diagnoses thermal, power, networking, BIOS, and BMC issues; develops documentation; collaborates with engineering and facilities teams; mentors junior staff; and supports on-call hardware milestones.

Provides advanced operational and engineering support for Arm-based AI hardware platforms in lab and data center environments. Leads hardware bring-up, break-fix troubleshooting, validation, root cause analysis, and reliability improvements across server blades, motherboards, power systems, and rack-scale infrastructure. Develops troubleshooting documentation, collaborates with engineering and infrastructure teams, mentors junior staff, and supports on-call activities during critical hardware milestones.

Lead systems engineer for blade and rack validation of ARM/x86 server compute racks. Drive first-silicon bring-up, firmware integration, lab and debug tool development, test plan ownership, triage and resolution of HW/FW/SW issues, and cross-functional coordination to meet program milestones and improve validation capabilities.

Leads global technical services teams supporting engineering labs, HPC platforms, and data center environments. Owns infrastructure reliability, security, capacity, procurement, budgets, supplier performance, operational standards, and lifecycle programs. Partners across engineering, IT, security, facilities, finance, supply chain, customers, and vendors to deliver resilient infrastructure for AI, silicon development, simulation, and validation workloads. The role is onsite in Austin and requires international travel.

Lead and conduct post-silicon validation for AI compute blades and racks, ensuring performance meets product standards while collaborating with multiple teams and mentoring engineers.

Lead electrical architecture and delivery for high-density AI data center infrastructure across design, construction, commissioning and operation. Develop standards, protection strategies, resilient power and energy-storage solutions; evaluate power-conversion technologies; direct consultants; support testing, site acceptance, operational readiness, incident investigations and cross-disciplinary collaboration. Mentor engineers and engage utilities, authorities and industry bodies.