ML Inference Engineer, C++/Python, Arm Acceleration

Arm Limited; Galway; Hybrid; EUR 85,000 - 125,000; Full time

Job summary

Arm Limited is seeking engineers to develop and optimize C++, C, and Python software that connects machine-learning platforms with Arm hardware acceleration. This role involves integrating ML frameworks and runtimes with Arm technology, including llama.cpp, and leading complex projects from design to delivery.

The ideal candidate will have strong C++, C, and Python skills, experience delivering features across teams, and knowledge of LLM inference.

Qualifications

• Strong C++, C, and Python programming and software-design skills.
• Experience delivering significant software features across multiple teams.
• Familiarity with Git, GitLab, continuous integration, and automated testing.
• Effective technical leadership and communication skills.
• Knowledge of LLM inference, including tokenization, attention, KV caches, batching and quantisation.

Responsibilities

• Develop and optimize C++, C, and Python software that integrates ML platforms with Arm hardware acceleration.
• Design and implement integrations between ML frameworks, runtimes, and hardware-acceleration technologies.
• Analyse and improve the performance of ML and LLM workloads.
• Lead significant work from design through delivery, mentor junior engineers, and support technical decisions.

Skills

C++

Python

Software design

Git/GitLab/CI/Testing

Technical leadership

LLM inference basics

Tools

llama.cpp

Job description

Arm Limited is seeking engineers to develop and optimize C++, C, and Python software that connects machine-learning platforms with Arm hardware acceleration. This role involves integrating ML frameworks and runtimes with Arm technology, including llama.cpp, and leading complex projects from design to delivery.

The ideal candidate will have strong C++, C, and Python skills, experience delivering features across teams, and knowledge of LLM inference.