Machine Learning Framework/Runtime Software Engineer (C++)

Arm’s approach to hybrid working is designed to create a working environment that supports both high performance and personal wellbeing. We believe in bringing people together face to face to enable us to work at pace, whilst recognizing the value of flexibility. Within that framework, we empower groups/teams to determine their own hybrid working patterns, depending on the work and the team’s needs. Details of what this means for each role will be shared upon application. In some cases, the flexibility we can offer is limited by local legal, regulatory, tax, or other considerations, and where this is the case, we will collaborate with you to find the best solution. Please talk to us to find out more about what this could look like for you.

We’re looking for C++ software development experience and good software engineering fundamentals. Experience could come from professional work, internships, academic projects, open-source contributions, or other practical software development.

An interest in machine learning software and how AI models run on different hardware is important. Some experience with, or exposure to, machine learning frameworks, runtime systems, compilers, GPU/compute software, or other performance-oriented technologies would be beneficial but is not essential.

In this role, you will contribute to developing, testing, and improving software across different parts of the machine learning software stack. Working alongside experienced engineers, you will help investigate functional and performance issues and contribute to solutions across runtimes, compilers, drivers, and hardware.

Good analytical and problem-solving skills, a willingness to learn, and an interest in machine learning systems, AI acceleration, and performance optimisation will help you grow in the role.

Beneficial but Not Required

We do not expect you to have experience across all the areas below. Relevant knowledge, practical experience, or exposure could include:

• Machine learning inference frameworks such as LiteRT, TensorFlow Lite, ONNX Runtime, or similar technologies
• GPU programming or compute technologies such as Vulkan, OpenCL, TOSA, or compute kernels
• Machine learning runtimes, compilers, drivers, or backend integration
• Computational graphs, operators, memory management, or model optimisation
• Ahead-of-Time or Just-in-Time compilation
• Benchmarking, profiling, testing, or analysing software performance
• Automated testing or CI/CD workflows
• AI-assisted development tools used responsibly to support software development, testing, and debugging

This role provides an opportunity to develop your skills in C++ software engineering, machine learning systems, and hardware-accelerated AI while working alongside experienced engineers.

You will gain exposure to machine learning inference engines and runtimes, compiler technologies, GPU and accelerator integration, model execution, performance optimisation, benchmarking, testing, and automated validation.

As your experience develops, you will have opportunities to take on increasingly complex engineering challenges and build a broader understanding of how machine learning frameworks, software, compilers, and hardware work together to deliver efficient AI experiences on Arm technology.

Working at Arm

At Arm, we want our people to learn, contribute, and grow while working on technologies shaping the future of AI and computing. The role offers opportunities for professional development, collaboration with colleagues across our global engineering community, and exposure to challenging technical problems with real-world impact.

Arm provides a comprehensive range of employee benefits and support designed to help our people thrive at work and beyond. Benefits vary by location and can include support for health and wellbeing, financial wellbeing, time away from work, and professional development.

We want our recruitment process to be accessible and inclusive. Reasonable accommodations are available throughout the recruitment process, and we encourage candidates who require support to let us know so that appropriate adjustments can be considered.