Software Engineer for AI Agentic Compute Platforms

Arm; Manchester; Ibrido; GBP 55.000 - 75.000; Tempo pieno

Descrizione del lavoro

Arm is seeking curious and motivated engineers to build the compute platform for AI at scale in Manchester. You will work on orchestrating models, data, tools and services across systems, contributing to AI workloads on Arm Neoverse platforms and AGI-CPU initiatives.

The role involves collaborating with open source communities and partners, with a focus on performance and scalable cloud-server technologies.

Competenze

• Strong software engineering and programming skills, preferably C++ and Python.
• Familiarity with Linux development environments, profiling, debugging and performance analysis.
• A degree in a computational or numerate subject, or equivalent experience.
• Experience with ML frameworks and LLM inference, such as PyTorch, vLLM, SGLang, llama.cpp or similar.
• Experience using heterogeneous CPU + accelerator systems.
• Familiarity with agentic AI frameworks and protocols.
• Interest in end-to-end performance from applications to hardware.
• Understanding of CPU bottlenecks in agentic workloads.
• Understanding of databases, vector search and retrieval systems.
• Familiarity with containers and cloud/server infrastructure.
• Understanding of parallel programming, collective communications or distributed AI workloads.
• Experience engaging with the open-source community.
• Familiarity with SIMD technologies, such as Neon, SVE and SME.

Conoscenze

C++

Python

Linux

Profiling

Debugging

Performance analysis

Neon

SVE

SME

PyTorch

vLLM

SGLang

llama.cpp

Formazione

Computational or numerate degree

Strumenti

Containers

Cloud infrastructure

Descrizione del lavoro

Arm is seeking curious and motivated engineers to build the compute platform for AI at scale in Manchester. You will work on orchestrating models, data, tools and services across systems, contributing to AI workloads on Arm Neoverse platforms and AGI-CPU initiatives.

The role involves collaborating with open source communities and partners, with a focus on performance and scalable cloud-server technologies.