Machine Learning Framework/Runtime Software Engineer Arm

Semiconductor Engineering; United Kingdom; Remote; GBP 70,000 - 110,000; Full time

Job summary

Semiconductor Engineering is seeking a skilled C++ software engineer with a track record building ML inference engines, runtime systems, or backend integration frameworks in the UK.

You will deepen expertise in how AI models execute in practice, covering graph processing, operator execution, memory management and cross‑framework integration while analyzing and resolving complex performance issues across frameworks, runtimes, compilers, drivers, and hardware abstraction layers.

Qualifications

• Proven C++ software development experience.
• Experience with ML inference engines and back-end integration.
• Familiarity with AI model execution, graph processing and memory management.

Responsibilities

• Analyze, investigate, diagnose, and resolve complex functional or performance issues across frameworks and runtimes.
• Collaborate with hardware abstraction layers and drivers to optimize inference workloads.

Skills

C++

ML inference

Backend integration

Tools

LiteRT

TensorFlow Lite

ONNX Runtime

Job description

We’re looking for strongC++ software development experience, ideally gained while building machine learning inference engines, runtime systems, or backend integration frameworks. Experience working with a machine learning inference framework such asLiteRT, TensorFlow Lite, ONNX Runtime, or a similar technologyis also important.

A good understanding of how AI models execute in practice is essential, including graph processing, operator execution, memory management, and backend integration. This role involvesanalysing, investigating, diagnosing, and resolving complex functional or performance issuesacross frameworks, runtimes, compilers, drivers, and hardware abstraction layers.