Machine Learning Framework/Runtime Software Engineer

Job Title

Machine Learning Framework/Runtime Software Engineer

Role Summary

Develop and optimise C++ components of machine learning runtimes and framework backends to enable efficient, hardware-accelerated inference. Work within a software engineering team in Cambridge collaborating with runtime, compiler, driver, and hardware teams to deliver integrated, high-performance solutions.

Experience Level

Mid-level (no specific years of experience stated)

Responsibilities

Deliver and maintain runtime and framework integration components; diagnose and resolve functional and performance issues across the AI software stack.

• Design, implement, integrate, test, and optimise runtime and backend components in a large modular C++ codebase.
• Analyse and diagnose complex functional and performance problems across frameworks, runtimes, compilers, drivers, and hardware abstraction layers.
• Collaborate with compiler, driver, and hardware teams to enable backend delegation and accelerator integration.
• Develop and maintain automated tests, benchmarking, and validation workflows to measure and improve model performance.
• Contribute to performance optimisation, memory management, operator execution, and graph processing efforts.

Requirements

Must-have technical skills and experience.

• Strong C++ software development experience.
• Experience with a machine learning inference framework such as LiteRT, TensorFlow Lite, ONNX Runtime, or similar.
• Practical understanding of AI model execution: graph processing, operator execution, memory planning, and backend integration.
• Proven ability to analyse, investigate, and resolve complex functional and performance issues across multiple software and hardware layers.
• Strong analytical and problem-solving skills and interest in performance optimisation for ML workloads.

Beneficial (nice-to-have).

• Experience developing delegates, execution providers, plugins, or backend integration mechanisms.
• GPU programming or familiarity with acceleration technologies (Vulkan, OpenCL, TOSA) and compute kernels.
• Knowledge of AOT/JIT compilation flows, graph transforms, operator partitioning, scheduling, or model optimisation.
• Experience with benchmarking, profiling, and validating AI model performance.
• Background in compiler technologies, intermediate representations, or hardware abstraction layers.

Education Requirements

Not specified.

About the Company

Company: Arm

Headquarters: Cambridge, United Kingdom

ARM is a global leader in semiconductor and software design, driving innovation in computing technology. The company specializes in designing processors and systems that provide the essential building blocks for electronic devices. ARM's architecture is widely used in smartphones, servers, and IoT devices, and its collaborative culture fosters bold thinking, diversity, and high-impact benefits for its talented workforce.