C++ ML Runtime Engineer - AI Acceleration & Systems

Arm Limited; Cambridge; On-site; GBP 70,000 - 120,000; Full time

Job summary

Arm is seeking a strong C++ software engineer in Cambridge to help build high-performance ML inference engines and backend integration frameworks. You will contribute across frameworks, runtimes, compilers and hardware abstractions to deliver optimized AI execution on Arm platforms.

You will analyse complex performance issues, work on graph processing and memory management, and collaborate with runtime, driver and hardware teams to push the boundaries of AI acceleration.

Qualifications

• Strong C++ software development experience.
• Experience with ML inference frameworks (LiteRT, TensorFlow Lite, ONNX Runtime).
• Understanding of AI model execution: graph processing, operator execution, memory management, backend integration.
• Ability to analyse, investigate, diagnose, and resolve complex functional or performance issues across frameworks, runtimes, compilers, drivers and HALs.

Responsibilities

• Design, develop, integrate, test, and optimise solutions within a large modular codebase.
• Collaborate with runtime, compiler, driver and hardware teams to deliver efficient AI execution.
• Analyse and resolve performance issues across AI software stack.

Skills

C++

ML runtime

Graph processing

Backend integration

Performance analysis

Tools

LiteRT

TensorFlow Lite

ONNX Runtime

Job description

Arm is seeking a strong C++ software engineer in Cambridge to help build high-performance ML inference engines and backend integration frameworks. You will contribute across frameworks, runtimes, compilers and hardware abstractions to deliver optimized AI execution on Arm platforms.

You will analyse complex performance issues, work on graph processing and memory management, and collaborate with runtime, driver and hardware teams to push the boundaries of AI acceleration.