Search
Go
Machine Learning Framework/Runtime Software Engineer (C++)
AArm
Summary by AIEngineer.careers
Machine Learning Framework/Runtime Software Engineer (C++) is a AI Infrastructure Engineer role (full-time). with Arm. in CAMBRIDGE, GB. Imported listing (source: careers.arm.com). Apply on the employer's site (careers.arm.com).
Imported listing (source: careers.arm.com) · Apply on careers.arm.com
CAMBRIDGE · GB
—
Full-time
MID
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from careers.arm.com
ARM is seeking a Machine Learning Framework/Runtime Software Engineer to develop and optimize the software stack that runs AI models on Arm hardware. The role focuses on C++ development for ML runtimes, compilers, and drivers, bridging the gap between high-level frameworks and low-level hardware acceleration. Candidates will work on performance optimization, benchmarking, and integration of technologies like Vulkan and OpenCL.
Responsibilities
- Develop and improve C++ software across the machine learning stack including runtimes, compilers, and drivers.
- Investigate and resolve functional and performance issues in AI model execution.
- Optimize computational graphs, memory management, and model operators for efficiency.
- Collaborate with teams on GPU/compute integration and backend support.
Requirements
- Strong C++ software engineering fundamentals and problem-solving skills.
- Experience with professional work, internships, or open-source contributions in software development.
- Interest in machine learning systems, AI acceleration, and hardware-software co-design.
- Ability to learn and adapt to new technologies within the ML ecosystem.
Benefits
A
Arm
Cambridge · GB · 9584+ employees
Arm Holdings plc is a leading semiconductor and software design company that creates central processing unit (CPU) intellectual property (IP), graphics processing units (GPU), and neural processing units (NPU). Its technology forms the foundational compute architecture used globally in smartphones, cloud data centers, automotive systems, and IoT devices.
