Machine Learning Framework/Runtime Software Engineer

ARM

Machine Learning Framework/Runtime Software Engineer Overview

Company Name ARM
Job Role Machine Learning Framework/Runtime Software Engineer
Qualifications Not Specified
Category IT Jobs
Job Type Full Time
Location Cambridge

At Arm, we are seeking an experienced Machine Learning Framework and Runtime Software Engineer skilled in C++ to join our team in Cambridge. This role involves developing and optimizing machine learning inference engines, runtime systems, and backend integration frameworks to ensure efficient execution of AI models. The successful candidate will analyze and troubleshoot complex functional and performance issues across various components such as frameworks, runtimes, compilers, drivers, and hardware abstraction layers. Collaboration with multidisciplinary teamsâ??including runtime, compiler, driver, and hardware engineersâ??is essential to design, develop, test, and integrate solutions within a large, modular codebase.

The role requires strong problem-solving skills, analytical thinking, and a deep interest in machine learning systems, AI acceleration, and performance optimization. Responsibilities include working on backend mechanisms like delegates, execution providers, and plugins, as well as engaging with GPU programming and acceleration technologies such as Vulkan, OpenCL, or TOSA where relevant. You will also contribute to designing or implementing Ahead-of-Time (AOT) and Just-in-Time (JIT) compilation workflows tailored for AI workloads, transforming computational graphs, managing operator partitioning, scheduling, memory planning, and optimizing models.

Additional tasks involve developing and maintaining automated testing frameworks and CI/CD pipelines for large-scale projects, applying AI-assisted development tools responsibly, and gaining a holistic understanding of how machine learning models move from high-level frameworks through software stacks to hardware acceleration. This role offers an excellent opportunity to deepen expertise in machine learning runtime development and hardware-accelerated AI execution, working across the entire AI software stack from framework-level model execution to backend delegation and compiler flows.

Working at Arm means being part of a forward-thinking environment that encourages learning, contribution, and growth while working on cutting-edge AI and computing technologies. The company provides a wide range of employee benefits, including support for health and wellbeing, professional development, and flexible working arrangements. The role is based in Cambridge, UK, with a hybrid working pattern that allows flexibility depending on team and project needs.

Arm is committed to diversity and inclusion, offering an accessible and supportive recruitment process. Reasonable accommodations are available throughout the hiring process to ensure all candidates can participate fully. If visa sponsorship is needed, Arm will cover the costs related to sponsorship for the employer, but the candidate will be responsible for visa application fees and the Immigration Health Surcharge.

Join us to influence the future of AI and computing, impacting a wide range of industries worldwide, from healthcare to virtual reality. Discover how our 10x mindset fosters curiosity, ambition, and impactful innovation, shaping a collaborative and inclusive work environment where bold ideas become reality.


Degree Requirement: Not Specified

Visa Sponsorship Promising

To apply for this job please visit careers.arm.com.