C++ ML Framework/Runtime Engineer - AI Performance

CamWebDir; United Kingdom; Hybrid; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Employee benefits

Job summary

Arm is seeking an Experienced Machine Learning Framework/Runtime Software Engineer (C++) to advance AI model execution across frameworks, runtimes, and hardware layers. You will work with teams across runtime, compiler, and hardware to optimise performance and reliability of ML workloads.

The role emphasizes strong C++ development, experience with inference frameworks, and collaboration in a large modular codebase, with hybrid working patterns and broad engineering impact at scale.

Qualifications

• Strong C++ software development experience.
• Experience with ML inference frameworks such as LiteRT, TensorFlow Lite or ONNX Runtime.
• Solid understanding of AI model execution, graph processing, memory management and backend integration.

Responsibilities

• Analyse, investigate, diagnose, and resolve complex functional or performance issues across frameworks, runtimes, compilers and hardware abstraction layers.
• Collaborate with runtime, compiler, driver and hardware teams to design, develop and optimise ML solutions.
• Contribute to tests, CI/CD and automation for large-scale software projects.

Skills

C++ software development

ML inference frameworks

Backend integration mechanisms

Tools

LiteRT

TensorFlow Lite

ONNX Runtime

Job description

Arm is seeking an Experienced Machine Learning Framework/Runtime Software Engineer (C++) to advance AI model execution across frameworks, runtimes, and hardware layers. You will work with teams across runtime, compiler, and hardware to optimise performance and reliability of ML workloads.

The role emphasizes strong C++ development, experience with inference frameworks, and collaboration in a large modular codebase, with hybrid working patterns and broad engineering impact at scale.