ML Runtime & Inference Systems Engineer – Hybrid

Arm; Cambridge; Hybrid; GBP 74,000 - 100,000; Full time

Job summary

Arm seeks a talented software engineer with strong C++ experience to join our machine learning runtime and backend integration efforts. You will help design, develop, and optimise ML inference components across a modular codebase, collaborating with runtime, compiler, driver, and hardware teams.

You'll work in a hybrid arrangement in the UK, contributing to performance improvements and model execution strategies, with opportunities to learn about acceleration technologies and AI workflows at Arm.

Qualifications

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

Responsibilities

• Design, develop, integrate, test, and optimise ML runtime/inference solutions across a large modular codebase.
• Collaborate with runtime, compiler, driver, and hardware teams to deliver performant AI workloads.

Skills

C++

ML inference

Performance analysis

Backend integration

Job description

Arm seeks a talented software engineer with strong C++ experience to join our machine learning runtime and backend integration efforts. You will help design, develop, and optimise ML inference components across a modular codebase, collaborating with runtime, compiler, driver, and hardware teams.

You'll work in a hybrid arrangement in the UK, contributing to performance improvements and model execution strategies, with opportunities to learn about acceleration technologies and AI workflows at Arm.