Graduate Software Engineer, AI Compute Libraries & Performance 2027
From £45k • Bristol, UK • Full-time
Posted 11d ago
About the job
Join Graphcore's Graduate Programme for a two-year, hands-on learning experience in AI Compute Libraries & Performance. You will contribute to C++ libraries and compute kernels for machine learning workloads, focusing on developing and optimizing operations, understanding performance bottlenecks, and ensuring the correctness and reliability of software that runs AI models on next-generation Graphcore hardware. This role offers a supportive team environment, mentorship, and opportunities to develop practical experience connecting numerical computing with hardware implementation.
Responsibilities
- Implement and improve compute kernels for machine learning operations like matrix multiplication and convolutions.
- Measure and analyze execution speed using profiling and microbenchmarks.
- Investigate the impact of threading, cache locality, memory layout, and kernel launch efficiency on performance.
- Build regression tests and numerical checks to ensure library quality and reliability.
- Contribute to high-performance compute libraries that enhance Graphcore hardware utilization.
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.
- Strong problem-solving skills and a collaborative approach to technical challenges.
Benefits
- Flexible working arrangements.
- Up to 5% matched pension.
- Phantom equity.
- On-site amenities including free food and a barista.
- Income protection and life assurance.
- Electric Vehicle Scheme (salary sacrifice).
- Flexible benefits package including private medical insurance and dental cover.
- Optional benefits: health cash plan, cycle to work scheme, give as you earn.