--- title: 'Graduate SoC Architecture Engineer 2027 at Graphcore' canonical: 'https://feeny.ai/job/graduate-soc-architecture-engineer-2027-graphcore-bristol-pbsht5rhmjzk' type: 'job' last_seen: '2026-11-10' --- # Graduate SoC Architecture Engineer 2027 at Graphcore - **Company:** Graphcore - **Location:** Bristol, United Kingdom - **Posted:** 2026-10-20 - **Last confirmed live:** 2026-11-10 - **Apply:** https://job-boards.greenhouse.io/graphcore/jobs/8894348002 ## Job description Location: Bristol, UK Salary: £45,000 per annum Start date: September 2027 Application deadline: Midnight, 29th November 2026 We encourage you to apply early, as we may close applications before the advertised deadline. The Graduate Programme at Graphcore Join Graphcore in a permanent role and start your career with two years of hands-on learning. From day one, you’ll be trusted to take ownership, share your ideas and help shape what we’re creating. You’ll tackle challenging problems alongside a team who support your development and are as excited about your success as you are. ## What you’ll work on Put your understanding of computer architecture to work on the choices that shape Graphcore’s next generation of AI hardware. As a Graduate SoC Architecture Engineer, you’ll help specify, model and evaluate complex system-on-chip (SoC) subsystems, with guidance from experienced architects. You’ll explore how product requirements translate into technical options, design trade-offs and validation plans. Your work will likely include some of: taking responsibility for the architecture of a chip subsystem or function, modelling architectural features, assessing third-party intellectual property (IP) and supporting silicon bring-up. Working across design, verification, hardware and software teams, you’ll help gather the performance evidence that supports architecture decisions. ## Your team and support The Silicon Architecture team sits within the Silicon group. We stand for practical ambition: clear thinking, careful engineering and curiosity that improves real systems. You’ll work with mentors and experienced architects through design reviews, modelling, simulation, documentation and discussions with neighbouring teams. You’ll take ownership of defined tasks that grow in scope as you develop your skills. Simulations, performance data and design constraints help guide our decisions. You’ll be encouraged to ask questions, challenge existing approaches and share ideas for making things better. Take responsibility for your work and speak up when something needs testing, explaining or support. ## How you’ll learn and grow During the two-year programme, you’ll develop your architecture skills through hands-on architectural design + integration, modelling and evaluation of AI acceleration hardware, supported by mentors. Exploring technical options and running simulations will help you understand how architecture choices affect system behaviour. You’ll learn how to compare trade-offs, document findings and use performance evidence to support a decision. Design reviews and work across engineering teams will help you connect specifications to implementation and validation. Supporting silicon bring-up will give you experience of how architectural ideas are checked on real hardware, while tasks that grow in scope will build your technical judgement and confidence. ## What we’re looking for - A degree, or expected degree, in Electronic Engineering, Computer Science or a related field - An understanding of computer architecture or digital systems, with an interest in SoC design, AI hardware or high-performance computing - Programming experience in Python, Rust, C++ or a similar language - Analytical problem-solving skills and clear written and verbal communication, including documenting findings and explaining technical ideas You can demonstrate these skills through coursework, a dissertation, personal or team projects, research, or other relevant experience. Tell us what you built or investigated, how you approached it and what you learned. Exposure to register-transfer level (RTL) design, modelling, simulation, PCIe, Ethernet or DDR would be useful. These are additional strengths, rather than essential requirements. ## Benefits - Flexible working: Balance your work and personal life with greater flexibility - Retirement planning support: Up to 5% matched pension - Phantom equity: Share in Graphcore’s success - Workplace experience: Enjoy thoughtfully designed office spaces for collaboration, with free food and an on-site barista to support your day - Peace of mind protection: Income protection and life assurance to provide financial security for you and your loved ones - Electric Vehicle Scheme: Choose an electric vehicle and lease it through salary sacrifice - Flexible benefits: Tailor your benefits package with a choice of additional options, including private medical insurance and dental cover - Optional benefits: Dental cover, health cash plan, private medical insurance, cycle to work scheme, give as you earn We welcome people from all backgrounds and experiences and are committed to building an inclusive environment where everyone can do their best work. We’re an equal opportunity employer and recognise that everyone brings different strengths and perspectives. If you need any adjustments during the interview process, just let us know - we’re happy to support you. Sponsorship Applicants must already have the right to work in the UK for the full duration of the programme, without requiring visa sponsorship. We are unable to sponsor work visas for our Early Careers opportunities. Introduction to Graphcore At Graphcore, we’re building next generation AI compute: from semiconductors and software to systems at datacenter scale. We are proud to be owned by SoftBank Group and work with other companies in the SoftBank family to deliver AI compute to customers working at the AI frontier. Starting your career here means working alongside people with different backgrounds and expertise, from AI researchers to chip designers and software engineers. You’ll learn from each other, bring fresh ideas and help solve challenging problems together. How to apply and what to expect To apply, answer the application questions below and upload your CV and cover letter. We’ll let you know the outcome of your application by early December at the latest. If successful, you’ll be invited to complete a technical assessment. Candidates who reach the final stage will then be invited to attend in-person assessments in early spring. Ready to put your learning into practice? Start your career in a permanent SoC Architecture Engineer role, with two years of hands-on learning through the Graphcore Graduate Programme. Apply now and help shape what comes next. ## 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 - [Technology Owner](https://feeny.ai/job/technology-owner-graphcore-bristol-n7932aqtncqw) — Bristol, United Kingdom - [Staff Engineering Program Coordination Support](https://feeny.ai/job/staff-engineering-program-coordination-support-graphcore-milpitas-6brm2n8e5s7y) — Milpitas, CA - [Corporate Travel Coordinator](https://feeny.ai/job/corporate-travel-coordinator-graphcore-bristol-3d3ffcpseesb) — Bristol, United Kingdom - [Lab Technician](https://feeny.ai/job/lab-technician-graphcore-bristol-1qse0fjvvph3) — Bristol, United Kingdom - [Programme Manager](https://feeny.ai/job/programme-manager-graphcore-bristol-vzkcxrjsjam9) — Bristol, United Kingdom - [Senior Network Operations Engineer](https://feeny.ai/job/senior-network-operations-engineer-graphcore-bristol-e40gft647ps9) — Bristol, United Kingdom - [Validation Chief of Staff](https://feeny.ai/job/validation-chief-of-staff-graphcore-austin-rmxtbeb85sjq) — Austin, TX - [Senior System Tests & Diagnostics Engineer](https://feeny.ai/job/senior-system-tests-diagnostics-engineer-graphcore-austin-2jtewzvghbe4) — Austin, TX - [Principal System Tests & Diagnostics Engineer](https://feeny.ai/job/principal-system-tests-diagnostics-engineer-graphcore-austin-by73g50t5bt3) — Austin, TX - [Staff Hardware Engineer](https://feeny.ai/job/staff-hardware-engineer-graphcore-austin-aznbnbmq9sx6) — Austin, TX