AI Compute Libraries Intern – Performance & ML (Summer)

Graphcore; West of England; Hybrid; GBP 25,000 - 30,000; Full time

Benefits offered by this job

Buddy support

Learning platform access

On-site facilities: free food, ice-ice

5 days annual leave

Job summary

Graphcore is offering a 12-week summer internship in Bristol, UK, focused on AI Compute Libraries & Performance. You will work on C++ libraries and compute kernels for machine learning workloads, contributing to performance and numerical correctness of low-level software on Graphcore hardware.

The role includes mentorship from experienced engineers, hands-on projects, and opportunities to learn profiling, testing, and optimization techniques.

Qualifications

• Currently pursuing a bachelor’s or master’s degree in Computer Science, Mathematics, Machine Learning, Data Science or a related field.
• Experience with C or C++11, plus familiarity with Python or scripting tools for automation and testing.
• An understanding of linear algebra, numerical methods or scientific computing.
• Problem-solving skills and collaborative approach to unfamiliar technical challenges.

Responsibilities

• Develop compute kernels: implement and improve operations such as GEMM, convolutions, reductions, elementwise ops and fused kernels.
• Understand and improve performance: use profiling and microbenchmarks to measure speed and explore threading, cache locality, memory layout and kernel launch efficiency.
• Check correctness and reliability: build regression tests and numerical checks, investigate issues and improve library quality.

Skills

C/C++11

Python scripting

Linear algebra

Numerical methods

Education

Bachelors or Masters in CS/Math/ML/DS or related

Tools

Profiling tools

Job description

Graphcore is offering a 12-week summer internship in Bristol, UK, focused on AI Compute Libraries & Performance. You will work on C++ libraries and compute kernels for machine learning workloads, contributing to performance and numerical correctness of low-level software on Graphcore hardware.

The role includes mentorship from experienced engineers, hands-on projects, and opportunities to learn profiling, testing, and optimization techniques.