22 days ago
Bristol, United KingdomIntern
Responsibilities
- Develop low-level kernel and user-space drivers and utilities connecting Graphcore AI hardware with machine-learning software.
- Write code, add unit tests, manually test changes, and fix software issues.
- Help maintain continuous integration and support software development workflows.
- Participate in technical design discussions, code reviews, and Scrum sessions.
- Collaborate with firmware, system QA, Poplar SDK, silicon, and hardware engineering teams.
Requirements
- Currently studying toward a bachelor’s or master’s degree in Computer Science, Maths, Machine Learning, Data Science, or a related field.
- Experience with low-level software such as embedded code or device drivers, through personal, university, or team projects.
- Introductory programming experience in C, C++, or Python.
- Basic electronics knowledge, including the ability to read schematics and datasheets.
- Awareness of continuous integration systems such as Jenkins.
- Experience using Git for source-code management, pull requests, reviews, and branch merging.
- Previous industry experience is not required.
Benefits
- 12-week internship based in Bristol, UK, starting in June 2027.
- £2,500 monthly salary.
- Five days of annual leave during the internship.
- Flexible working arrangements.
- Office collaboration spaces with free food, ice cream, and an on-site barista.
- Access to O’Reilly for learning and development.
- Potential opportunity to join a graduate programme after graduation, depending on performance and available roles.
About Graphcore
Graphcore designs and sells Intelligence Processing Units (IPUs), systems, and a full software stack for training and inference of AI models in data centers and research labs. Revenue comes from hardware systems and associated software tools and services, used for workloads across NLP, computer vision, and graph neural networks. Founded in 2016 and headquartered in Bristol, the company is part of SoftBank Group and focuses on on‑prem and cloud deployments.