22 days ago
Bristol, United KingdomIntern
Responsibilities
- Develop and improve C++ compute kernels for machine learning workloads, including GEMM, convolutions, reductions, elementwise operations, and fused kernels.
- Profile code and use microbenchmarks to measure execution speed and investigate threading, cache locality, memory layout, and kernel launch efficiency.
- Build regression tests and numerical checks, investigate issues, and improve compute library quality and reliability.
- Use profiling, experiments, technical reviews, and numerical validation to assess performance trade-offs and preserve correct results.
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 C or C++11 and familiarity with Python or scripting tools for automation and testing.
- Understanding of linear algebra, numerical methods, or scientific computing.
- Problem-solving skills and a collaborative approach to unfamiliar technical challenges.
- Coursework or experience with machine learning frameworks, parallel programming, code optimisation, maths libraries, or performance analysis is useful but not essential.
- Previous industry experience is not required; relevant coursework, personal projects, team projects, or investigations may demonstrate experience.
Benefits
- 12-week summer internship starting June 2027 in Bristol, UK.
- £2,500 per month salary and 5 days of annual leave during the internship.
- Flexible working arrangements, collaborative office spaces, free food, ice cream, and an on-site barista.
- Access to O’Reilly for learning and development.
- Buddy support, regular manager meetings, technical guidance, feedback, and an inclusive working environment.
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.