Staff ML Frameworks Engineer - LLM & Acceleration

Arm Limited; Galway; Hybrid; EUR 90.000 - 130.000; Vollzeit

Zusammenfassung

Arm Limited is seeking engineers to help shape the future of ML and AI on Arm platforms. You will develop and optimize software that connects ML frameworks and runtimes to Arm hardware acceleration, including llama.cpp integrations, and lead projects from design to delivery.

The role requires strong skills in C++, C, and Python, plus experience with multi-team software delivery, Git/GitLab/CI, and LLM concepts. A collaborative, fast-paced environment awaits.

Qualifikationen

• Proven ability to deliver software features across multiple teams.
• Experience with Git, GitLab, CI, and automated tests.
• Strong analytical and problem-solving skills; able to lead significant projects end-to-end.
• Knowledge of LLM inference concepts such as tokenization, attention, KV caches, batching, and quantisation.

Aufgaben

• 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.
• Analyze and improve performance of ML and LLM workloads.
• Lead significant work from design through delivery; mentor junior engineers; support technical decisions.

Kenntnisse

C++

Python

Software design

Software delivery across teams

Git, GitLab, CI, tests

Technical leadership

LLM inference basics

Tools

llama.cpp

Jobbeschreibung

Arm Limited is seeking engineers to help shape the future of ML and AI on Arm platforms. You will develop and optimize software that connects ML frameworks and runtimes to Arm hardware acceleration, including llama.cpp integrations, and lead projects from design to delivery.

The role requires strong skills in C++, C, and Python, plus experience with multi-team software delivery, Git/GitLab/CI, and LLM concepts. A collaborative, fast-paced environment awaits.