22 days ago
Bristol, United KingdomEntry Level
Responsibilities
- Develop and improve C++ compute kernels for GEMM, convolutions, reductions, elementwise operations, and fused operations.
- Profile and benchmark code to investigate threading, cache locality, memory layout, and kernel launch efficiency.
- Build regression tests and numerical checks to validate correctness and reliability.
- Investigate performance and correctness issues in high-performance compute libraries.
- Collaborate with performance and low-level software engineers through technical reviews, experiments, and scoped projects.
Requirements
- Bachelor’s or master’s degree in Computer Science, Maths, Machine Learning, Data Science, or a related field.
- Experience with C++11.
- Familiarity with Python or scripting tools for automation and testing.
- Understanding of linear algebra, numerical methods, or scientific computing.
- Problem-solving and collaboration skills demonstrated through coursework, dissertations, personal or team projects, research, or other relevant experience.
- Coursework or experience with machine learning frameworks, parallel programming, code optimisation, maths libraries, or performance analysis is useful but not essential.
Benefits
- Permanent role beginning in September 2027 with a two-year graduate development programme.
- Flexible working arrangements.
- Up to 5% matched pension contribution.
- Phantom equity.
- Designed office spaces, free food, and an on-site barista.
- Income protection and life assurance.
- Electric vehicle salary-sacrifice scheme.
- Optional private medical insurance, dental cover, health cash plan, cycle-to-work scheme, and give-as-you-earn options.
- Applicants must already have the right to work in the UK for the full programme; work visa sponsorship is not available.
- Application deadline is midnight on 29 November 2026, with in-person assessments expected in early spring.
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.