---
title: 'Principal Storage Architect at Graphcore'
canonical: 'https://feeny.ai/job/principal-storage-architect-graphcore-milpitas-arz44316fpcr'
type: 'job'
last_seen: '2026-10-13'
---

# Principal Storage Architect at Graphcore

- **Company:** Graphcore
- **Location:** Milpitas, CA
- **Posted:** 2026-10-07
- **Last confirmed live:** 2026-10-13
- **Apply:** https://job-boards.greenhouse.io/graphcore/jobs/8876971002

## Job description

## About Graphcore

Graphcore is a leading innovator in artificial intelligence computing. We develop hardware, software, and data center infrastructure that provide the specialized processing and systems capabilities needed to advance AI while improving the efficiency required for broad adoption.

As part of SoftBank Group, Graphcore works alongside companies developing advanced technologies. Our teams bring together AI researchers, silicon designers, hardware and software engineers, and systems architects to solve complex technical problems across the computing stack.

The Opportunity

As Principal Storage Architect, you will define the high-performance storage architecture for Graphcore's AI computing and data center infrastructures.   You will lead the design of local and distributed storage tiers that provide the throughput, availability, and predictable tail latency required for large-scale training and inference.

Working within Advanced Architecture, you will address storage requirements for saving model states, offloading key-value caches, large datasets, and high-speed data-loading pipelines.   You will combine hands-on performance engineering with Principal-level technical leadership across hardware, software, networking, systems engineering, automation, supply chain, and external technology partners.

## What You Will Do

- Define the end-to-end architecture and technology roadmap for local, disaggregated, and distributed storage across Graphcore AI server and data center platforms.
- Design storage topologies that optimize PCIe lane allocation, network-domain placement, and data paths among CPUs, AI accelerators, memory, and storage systems.
- Lead the architecture of storage control-plane and data-plane solutions, evaluating commercial and open technologies against performance, resilience, manageability, and lifecycle requirements.
- Profile and tune the Linux storage stack, block layer, I/O schedulers, direct I/O paths, file systems, and drivers to improve IOPS, bandwidth, and 99.99th-percentile latency.
- Optimize storage for AI workloads, including model checkpointing, key-value cache offload, data ingestion, and direct data movement between NVMe storage and accelerator memory.
- Set the technical direction for NVMe SSD lifecycle management, including qualification, provisioning, health monitoring, firmware rollout, failure handling, and warranty-return automation across E1.S, E3.S, U.2, and U.3 devices.
- Define telemetry and alerting requirements for direct-attached and distributed storage, including endurance, wear, drive writes per day, thermals, capacity, performance, and latency anomalies.
- Provide architecture requirements and technical guidance to automation teams building frameworks that characterize storage performance, reliability, and compatibility across AI platforms.
- Lead root-cause analysis for complex storage failures and performance degradation across Linux kernels, drivers, PCIe, networks, SSD firmware, and third-party storage systems.
- Partner with storage vendors, supply chain, networking, systems engineering, and product teams to select, integrate, and deploy storage components and platforms.
- Evaluate emerging storage, interconnect, and memory-tiering technologies and translate relevant developments into platform requirements and future system designs.

## What You Will Bring

- A bachelor's or equivalent experience or master's degree in computer science, computer engineering, information technology, electrical engineering, or a related field, or equivalent practical experience.
- Extensive hands-on experience in storage engineering and architecture for AI, high-performance computing, hyperscale, or large data center environments, including technical leadership at Principal, Staff, or Lead Architect scope.
- Deep knowledge of NVMe, PCIe Gen5 or Gen6 architecture, NAND flash behavior, SSD form factors, endurance, firmware, and device lifecycle management.
- Deep operational knowledge of Linux storage internals, including the block layer, I/O schedulers, direct I/O, kernel and driver behavior, and file systems such as XFS, ext4, or ZFS.
- Hands-on experience with storage benchmarking and profiling tools such as fio, blktrace, iostat, and perf, including the ability to design representative workload models and isolate bottlenecks.
- Programming and automation skills in Python and Bash, with experience using structured data formats and REST APIs to build monitoring, validation, or lifecycle workflows.
- Demonstrated ability to diagnose complex hardware and software interactions, including kernel failures, PCIe errors, network issues, performance regressions, and SSD firmware defects.
- Experience defining telemetry signals, alert thresholds, dashboards, and operational response criteria for storage health and performance at fleet scale.
- Proven ability to lead cross-functional architecture decisions, influence senior engineers and leaders, and communicate technical risks, tradeoffs, and recommendations clearly.

## Preferred Qualifications

These qualifications are helpful, not required. We encourage you to apply even if you do not meet every preferred qualification.

- Experience implementing, testing, or troubleshooting GPU Direct Storage or comparable direct accelerator-to-storage technologies.
- Experience designing or operating NVMe over Fabrics deployments using RoCEv2 or TCP.
- Experience with the Storage Performance Development Kit or other user-space storage frameworks.
- Familiarity with high-performance parallel and distributed file systems such as Weka, VAST Data, Lustre, DAOS, DDN, or comparable platforms.
- Knowledge of Compute Express Link and its implications for future memory and storage tiering in AI servers.

United States Benefits Overview

Graphcore offers compensation and benefits designed to support employees' health, financial well-being, work-life needs, and professional growth. Benefits and programs for eligible U.S. employees may include:

- Medical, dental, and vision coverage, with options that may extend to eligible dependents.
- Mental health, wellness, and employee assistance resources.
- Retirement savings benefits and company contributions where applicable.
- Paid vacation, sick time, company holidays, and parental or family leave in accordance with applicable plans and policies.
- Life insurance and short-term or long-term disability coverage.
- Flexible working hours and hybrid working arrangements where compatible with the role and team requirements.
- Professional development resources, learning programs, office amenities, and team-led activities.

Benefits vary by work location, employment status, scheduled hours, and plan eligibility and are subject to the terms of the applicable plans and company policies. This overview is not a contract or guarantee of benefits.

## Equal Opportunity and Accommodations

Graphcore is an equal opportunity employer. We consider qualified applicants without regard to race, color, religion, creed, sex, pregnancy, sexual orientation, gender identity or expression, national origin, ancestry, age, disability, genetic information, veteran status, or any other status protected by applicable law.

Graphcore is committed to an inclusive and accessible hiring process. If you need a reasonable accommodation to participate in the application or interview process, please let the recruiting team know.

Candidate Privacy

Personal information submitted during the recruiting process will be handled in accordance with Graphcore's applicable candidate privacy notices.

## About Graphcore

## Company Overview
- **One-liner**: Graphcore designs and builds the Intelligence Processing Unit (IPU), a processor purpose-built for machine intelligence, and provides a complete AI compute stack from silicon to software.
- **Entity Type**: Private (wholly owned subsidiary of SoftBank Group Corp as of 2025/2026)
- **Headquarters**: Bristol, England, UK
- **Founded**: 2016
- **Founders**: Nigel Toon and Simon Knowles

## Core Business
- **Primary industry**: AI hardware/accelerators, semiconductor design, AI software platform
- **Target customers**: Cloud providers (Microsoft Azure), enterprises, AI researchers, hyperscalers
- **Mission statement**: “Let innovators create the next breakthroughs in machine intelligence to enhance human potential”

## Products & Services
- **[IPU (Intelligence Processing Unit)](https://www.graphcore.ai/)**: A processor designed from the ground up for machine intelligence workloads; uses a massively parallel architecture (MIMD) with fine-grained compute and on-chip memory.
- **[IPU-Machine M2000](https://www.graphcore.ai/about)**: Second-generation IPU platform – a 1U server appliance housing 4 MK2 GC200 IPU processors, delivering an 8× performance uplift over the first generation.
- **[C2 IPU Accelerator PCIe Card](https://www.graphcore.ai/about)**: PCIe form factor accelerator for server integration, first demonstrated at ICML 2018.
- **[Poplar Software Stack](https://www.graphcore.ai/)**: Full SDK and framework integration (PyTorch, TensorFlow) that lets developers target the IPU directly.

## Market Standing
- **Valuation/Market Cap**: Acquired by SoftBank Group Corp (amount undisclosed); prior to acquisition valued at $2.77 B (Series E, lead by Ontario Teachers’ Pension Plan Board).
- **Key Metric**: Total funding raised prior to acquisition – over $680 M across Series A through E.
- **Notable Investors/Partners**: SoftBank (owner), Microsoft (customer and investor), BMW, Samsung, Dell Technologies, Bosch, Sequoia Capital, Atomico, Fidelity, Baillie Gifford, Ontario Teachers’.
- **Growth Signals**: Part of the fast-growing SoftBank AI ecosystem; expanding teams globally (Bristol, London, Cambridge, Gdańsk, Hsinchu, Bengaluru); first customer (Microsoft Azure) live since 2018.

## Competitive Advantages
- **First purpose-built AI processor**: The IPU architecture is fundamentally different from GPUs – designed specifically for the sparse, parallel nature of neural network computation.
- **Full stack ownership**: Graphcore controls silicon, system hardware, and software (Poplar), enabling tight optimisation across the entire compute chain.
- **Cloud + on‑prem availability**: IPUs are available in the cloud on Microsoft Azure and as hardware from Dell, giving customers flexible deployment options.
- **Strong IP and ecosystem**: 99+ engineering staff; deep expertise in semiconductor, systems, and AI software, backed by long-term SoftBank investment.

## Strategic Focus
- **Scale AI infrastructure**: Delivering key technology into SoftBank’s global AI ecosystem and expanding the IPU platform to meet growing demand for AI compute.
- **Expand into new regions**: Opening offices and hiring in India (Bengaluru) and across Europe (Gdańsk, London, Cambridge) to accelerate R&D and customer support.
- **Democratise AI**: Continuing to lower the barrier for machine intelligence by providing accessible, high-efficiency hardware and software for innovators worldwide.

## Why Work Here
- **Flexible hybrid work**: Employees are expected on-site three days a week, with trust and flexibility to balance work and life.
- **Comprehensive benefits**: Unlimited annual leave, private medical insurance (UK), dental & health cash plan, income protection, life assurance, pension matched up to 5%, generous parental leave, and a personal development plan.
- **Culture and growth**: ML reading groups, board game socials, book clubs, yoga, running, watersports, team events; strong DE+I initiatives; ambitious but supportive environment.
- **Perks**: Free barista‑made coffee, snacks, and wellbeing rooms; cycle‑to‑work scheme; gym membership discount; education/training allowances.
- **Purpose-driven work**: Opportunity to shape the future of AI compute and see your contributions used by global innovators.

## Sources
1. [graphcore.ai/about](https://www.graphcore.ai/about)
2. [graphcore.ai/](https://www.graphcore.ai/)
3. [graphcore.ai/careers](https://www.graphcore.ai/careers)
4. [graphcore.ai/jobs](https://www.graphcore.ai/jobs)
5. [builtin.com/company/graphcore](https://builtin.com/company/graphcore)

## Other roles at Graphcore

- [Staff Manufacturing Product Engineer](https://feeny.ai/job/staff-manufacturing-product-engineer-graphcore-bristol-ea1bm22k33gw) — Bristol, United Kingdom
- [Senior Manufacturing Product Engineer](https://feeny.ai/job/senior-manufacturing-product-engineer-graphcore-tainan-d577fdezv8tm) — 臺南市 Tainan, Taiwan
- [Technical Product Owner](https://feeny.ai/job/technical-product-owner-graphcore-bristol-9v35a207cdk8) — Bristol, United Kingdom
- [Senior Machine Learning Engineer (Large Systems)](https://feeny.ai/job/senior-machine-learning-engineer-large-systems-graphcore-cambridge-3e8ndgscz15d) — Cambridge, MA
- [Senior Machine Learning Engineer (Large Systems)](https://feeny.ai/job/senior-machine-learning-engineer-large-systems-graphcore-london-p68byjrjd25g) — London, United Kingdom
- [Senior Machine Learning Engineer (Large Systems)](https://feeny.ai/job/senior-machine-learning-engineer-large-systems-graphcore-bristol-s0r6v5tfnmv9) — Bristol, United Kingdom
- [Staff AI Performance Engineer](https://feeny.ai/job/staff-ai-performance-engineer-graphcore-milpitas-fsnhys3s671g) — Milpitas, CA
- [Principal AI Performance Engineer](https://feeny.ai/job/principal-ai-performance-engineer-graphcore-austin-nkrwx6t7hyy0) — Austin, TX
- [Senior AI Performance Engineer](https://feeny.ai/job/senior-ai-performance-engineer-graphcore-austin-st5fb702pk3z) — Austin, TX
- [Principal System Tests & Diagnostics Engineer](https://feeny.ai/job/principal-system-tests-diagnostics-engineer-graphcore-austin-9y5qhh1chbx8) — Austin, TX