AI Engineer (C++ )

AI Engineer (C++)

6 Month Contract

Outside IR35

UK Fully Remote

About the Role

Fruition are seeking a skilled C++ engineer for our client to help build and optimize the runtime layer powering local AI on edge devices. This role focuses on porting, enhancing, and optimizing inference engines such as llama.cpp, ggml, and ONNX-based runtimes to deliver fast, efficient, and reliable on-device AI performance across diverse hardware environments.

You will work close to the metal, improving model loading, memory efficiency, and inference speed while ensuring runtime stability and production readiness. This is an opportunity to contribute to privacy-focused AI systems that operate independently of cloud infrastructure.

Responsibilities

• Deploy and optimize machine learning models for edge and on-device environments using frameworks including llama.cpp, ggml, and ONNX
• Improve inference runtime performance across different CPU and GPU architectures
• Collaborate closely with AI researchers to transition models from research into production-ready deployments
• Support model integration, optimization, and runtime stability throughout the deployment lifecycle
• Integrate advanced AI capabilities into existing products and systems
• Contribute to the ongoing enhancement of local inference infrastructure and tooling

Requirements

• Strong programming skills in C++ with experience building high-performance systems
• Hands-on experience with inference engines such as llama.cpp and ggml
• Understanding of deploying models to specific GPU architectures and optimizing inference workloads
• Solid knowledge of deep learning concepts, transformer architectures, and large language models (LLMs)
• Experience working with ONNX and related model deployment frameworks
• Ability to quickly learn and adapt to new technologies and techniques
• Degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field, or equivalent practical experience
• Proven background in AI research and development or production ML systems

Nice to Have

• Experience with JavaScript or cross-platform application integration
• Familiarity with low-level performance optimization and hardware acceleration
• Experience working on edge AI, embedded systems, or privacy-focused AI products