Principal Propeller Engineer

Graphcore

About Graphcore  At Graphcore, we’re building the future of AI compute.We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack - from silicon and software to infrastructure at datacenter scale. As part of the SoftBank Group, backed by significant long-term investment, we are delivering key technology into the fast-growing SoftBank AI ecosystem.To meet the vast and exciting AI opportunity, Graphcore is expanding its teams around the world.We are bringing together the brightest minds to solve the toughest problems, in a place where everyone has the opportunity to make an impact on the company, our products and the future of artificial intelligence.    Job Summary   We are looking for an experienced Principal Engineer to join our Cloud Platform Team and help develop and deploy clouds and services. Working closely with our colleagues in Software Platform, Datacentre Operations and Product Development teams, you will deploy services on our fleet of cutting-edge AI systems. As part of our Software Platform organisation, you will be involved in the cloud integration, validation, performance benchmarking, optimisation, and development of our high-performance AI solutions.  These include in-house AI systems alongside off-the-shelf high-performance servers, switches and storage solutions.  This is a hand-on technical role requiring a solid background in the use of cloud infrastructure, deployment using Infrastructure-as-Code, observability, high-performance networking and storage systems.  You may have been working in an IT organisation, a datacentre, a cloud provider or as a developer of orchestration or cloud services.      The Software Platform team at Graphcore  We build Graphcore products into large-scale AI solutions for our customers and the Cloud Platform Team is responsible for providing such systems to both internal users via private clouds and customers via our own public clouds.  Often the internal systems will be using and developing pre-release hardware and software, so it’s vital you are comfortable with unproven components.    Responsibilities and Duties * Operate and extend existing OpenStack-based cloud services and contribute to the deployment and development of new ones.  * You will be responsible for significant technical initiatives and projects, mentoring a small team of more junior engineers in best engineering practices.  * Develop and operate end-user services on our clouds and support internal users in their use. You will turn end-user and product requirements into deployed services.  * Help to build automation to collect and analyse metrics and other observability data from the cloud services to support clear identification and reporting of any issues.  Work with users to provide information of any product-related issues to Engineering and QA departments.  * Work with our Datacentre Operations Engineers to maintain and operate the fleet of AI systems at peak performance in our private clouds.  * Configure and test new Graphcore AI hardware and systems using Continuous Deployment and Infrastructure-as-code in internal and external datacentres.  * Drive corrective actions for systems that are not operating correctly, working with DC operations and Graphcore Engineering as required.  * Work with external vendors of off-the-shelf switches, servers and storage solutions to specify, benchmark and integrate 3rd party products into our Cloud Reference Design.    Skills and Experience [ALL REQUIRED]  * Bachelor's degree or equivalent practical experience in a relevant subject.  * Solid infrastructure or IT experience with a proven track record of delivering technical output as an individual contributor.  * Experience managing or operating on-premises or private-cloud environments.   * Experience specifying, scoping, estimating and detailing work plans in an AGILE and SCRUM framework, including priorities, risks, issues, impacts and constraints.  * Expert-level, proven Linux scripting ability (bash and python required).  * Expert-level, proven Linux system administration (Ubuntu, RHEL and variants).  * Experience with a version control system (preferably Git) and using it to manage system configuration or automation.  * Experience with Continuous Integration or testing pipelines using GitLab, GitHub or similar.  * Hands-on experience deploying services into public or private clouds using Infrastructure-as-Code (IAC).  * A solid understanding of the technologies underpinning cloud services (APIs, virtualisation of CPUs, IO, systems), virtual networks, block storage, resource management and monitoring.  * Expert with IAC automation tools (e.g. Terraform/OpenTofu, Ansible, Packer).  * Experience with container deployment and management tools (e.g. docker, podman, apptainer).  * Experience with solutions for monitoring and observability. e.g. Grafana, Prometheus, OpenSearch/ElasticSearch, Loki, Mimir, OpenTelemetry, Fluentd ,Kafka  * Excellent communication and presentation skills, and experience dealing with end-users of IT or cloud services.  * An ability to work independently and lead others on critical infrastructure without oversight, and with a focus on end-user availability.     Desirable but not required:  * Experience with OpenStack deployments or the technologies they rely on (e.g. Ceph, Open vSwitch, KVM, QEMU ).   * Experience with High Performance Computing (HPC) environments using SLURM or similar batch workload solutions.  * Strong skillset and experience in end-to-end deployment automation and CI of containerised services. Complete automation of pipelines for build, test, deploy, manage, alert, destroy, rebuild.  * Experience with managing production Kubernetes clusters and workloads.   * Experience with workload queue management systems (SLURM, LSF, Kueue).   * Experience with managed switch configuration (e.g. EOS, SONiC, DNOS).   * Programming experience with Python3 utilising classes and inheritance.  * Programming experience with Go.    Benefits In addition to a competitive salary, Graphcore offers flexible working, a generous annual leave policy, private medical insurance and health cash plan, a dental plan, pension (matched up to 5%), life assurance and income protection. We have a generous parental leave policy and an employee assistance programme (which includes health, mental wellbeing, and bereavement support). We offer a range of healthy food and snacks at our central Bristol office and have our own barista bar! 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.   Sponsorship Applicants for this position must hold the right to work in the UK. Unfortunately at this time, we are unable to provide visa sponsorship or support for visa applications.

Graphcore

ABOUT GRAPHCORE At Graphcore, we’re building the future of AI compute.We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack - from silicon and software to infrastructure at datacenter scale.As part of the SoftBank Group, backed by significant long-term investment, we are delivering key technology into the fast-growing SoftBank AI ecosystem.To meet the vast and exciting AI opportunity, Graphcore is expanding its teams around the world.We are bringing together the brightest minds to solve the toughest problems, in a place where everyone has the opportunity to make an impact on the company, our products and the future of artificial intelligence. Job Summary    As Principal Product Engineer, you will be responsible for ensuring that Graphcore products are manufactured with optimised yield, quality and cost, throughout the product lifecycle. You will work closely with OSATs, test engineering, manufacturing and quality teams to release new products and sustain high volume production.  This is a highly technical role requiring deep expertise in semiconductor product engineering, manufacturing analytics, and system-level test and manufacturing processes. You will provide technical leadership across manufacturing operations, helping define best practices, solve complex yield and quality challenges, and improve manufacturing efficiency and product reliability.    The Team  The role will be as part of the Product Test and Diagnosis team, which is part of the Graphcore Manufacturing Operations department and has members in Bristol, Cambridge, India, US and Taiwan. The team is responsible for definition, development, and execution of an end-to-end test strategy spanning silicon, board-level assemblies, server blades, and rack-scale systems. Testing is performed across the full product lifecycle, including manufacturing, and deployed field environments.    Responsibilities and Duties  * Drive yield, quality and cost optimisation across the product lifecycle, including chip manufacturing, test, PCBA and system level manufacturing  * Work closely with test engineering to define requirements for coverage, reporting and datalog formats from both ATE and system level electrical test   * Own analytics for SMT manufacturing processes, including SPI/AOI/AXI/ICT etc  * Own analytics for board and system level testing, including boundary scan and functional testing at board/blade/rack level  * Work with technology and manufacturing specialists to manage low yield events in production and drive overall yield improvement  * Support RMA analysis and reliability/qualification activities  * Establish best practices for data collection, cleaning, correlation, and visualization  * Collaborate with the Data Engineering and Analytics team to develop loading scripts for new data sources and optimise database schemas   * Define and develop standard analyses such as dashboards and enable fast self-service access to data for end users  * Regular travel to OSATs and manufacturing partners will be required    Essential Skills and Experience  * Solid experience (10+ years) in semiconductor product engineering, test engineering, or manufacturing engineering  * Solid experience in high-volume semiconductor/electronics manufacturing, data visualization tools, and manufacturing systems/databases (MES)  * Solid understanding of semiconductor, PCBA and system level manufacturing and testing  * Solid expertise in statistical analysis (SPC, DOE, regression, hypothesis testing) and six sigma methodologies  * Solid expertise in analysing and visualising large manufacturing datasets  * Proficiency in data tools such as Python, SQL, JMP, or similar.  * Demonstrated success driving yield and cost improvements in high-volume production  * Degree in Electrical Engineering, Computer Science, Physics or similar    Desirable:  * Extensive experience and expertise in JMP and in using the JMP scripting language to build standard analysis reports, dashboards and applications  * Experience in using data visualisation tools such as Apache Superset    BENEFITS In addition to a competitive salary, Graphcore offers flexible working, a generous annual leave policy, private medical insurance and health cash plan, a dental plan, pension (matched up to 5%), life assurance and income protection. We have a generous parental leave policy and an employee assistance programme (which includes health, mental wellbeing, and bereavement support). We offer a range of healthy food and snacks at our central Bristol office and have our own barista bar! 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.

Graphcore

About Graphcore At Graphcore, we’re building the future of AI compute.We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack - from silicon and software to infrastructure at datacenter scale.As part of the SoftBank Group, backed by significant long-term investment, we are delivering key technology into the fast-growing SoftBank AI ecosystem.To meet the vast and exciting AI opportunity, Graphcore is expanding its teams around the world.We are bringing together the brightest minds to solve the toughest problems, in a place where everyone has the opportunity to make an impact on the company, our products and the future of artificial intelligence.   Job Summary   Our team is at the forefront of the artificial intelligence revolution, enabling innovators from all industries and sectors to expand human potential with technology. The availability of specialised artificial intelligence compute will be a decisive factor in AI’s rate of progress. Graphcore allows innovators to go further, faster. What we do really makes a difference. Reporting to the Director of Silicon Architecture, the SoC Architects are responsible for the design, specification, modelling and integration of sub-systems within complex, high performance and highly integrated silicon devices at the forefront of AI acceleration technology. The role involves close collaboration with other groups, including architecture, silicon design, verification, hardware and software teams.   The Team The Silicon Architecture Team sits within the COO group. The SoC architects are responsible for the architectural specification, integration, modelling, validation and evaluation of numerous critical sub-systems, including high-speed interfaces for our upcoming AI acceleration platforms.    Responsibilities and Duties  * Defines team infrastructure and processes   * Distilling product requirements and their effects on SoC/platform design trade-offs  * Collaborating with processor, SoC and system architects to determine optimal solutions  * When required, providing technical knowledge silicon design, verification, and hardware engineers to ensure implementation correctness   * Good experience potential hard and soft third-party IP and liaising with third party IP vendors  * Design and specification of performant SoC sub-systems and their associated integrations  * Manages queries for the silicon bring-up, characterisation and evaluation activities as required  * Drives delivery and planning of technical objectives  * Advise in planning for infrastructure and processes   * Silicon Architecture Team representation within cross-functional working groups  * Mentors' senior technical engineers     Candidate Profile     Essential:  * Degree in Electronic Engineering, Computer Science or related subject  * Experience in the technical specification of complex silicon SoC devices  * Strong software development experience  * Solid understanding of complex computer/SoC architecture  * Excellent communication skills  * Strong experience in writing and developing technical specifications  * In depth knowledge of RTL development and verification processes  * Be a self-starter, able to motivate and support team members   * Ability to work across teams and programming languages    Desirable  * Architecture modelling experience in Python/C++/Rust  * Experience of machine learning or massively parallel computing systems  * Verilog  * Knowledge of one or more of DDR, PCIe, Ethernet, on-chip networks  Benefits In addition to a competitive salary, annual leave policy, medical and dental health plans, a gym card and employee pension (matched up to 4%). We review our benefits on a yearly basis to ensure we offer a valuable and rewarding benefits programme to our employees.  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.