Edinburgh: AI Systems Research Engineer (LLM Infra)

European Tech Recruit; Dunfermline; On-site; GBP 90,000 - 130,000; Full time

Job summary

European Tech Recruit is assisting a leading telecommunications company in Edinburgh to hire a Systems Research Engineer focused on AI infrastructure and C++ systems engineering. You will help build scalable distributed architectures and contribute to a world-class research program in a dynamic data-center setting.

The ideal candidate has a CS/EE degree (PhD preferred), strong C/C++ skills, Python for prototyping, and hands-on experience with LLM serving tools such as vLLM and Ray Serve.

Qualifications

• Bachelor’s or Master’s in CS/EE (PhD preferred).
• Strong proficiency in C/C++ for systems work and Python for prototyping.
• Hands-on experience with LLM serving frameworks (vLLM, Ray Serve, TensorRT-LLM) and distributed algorithms.

Responsibilities

• Architect scalable distributed architectures for CPU/GPU/NPU clusters.
• Perform in-depth profiling of large-scale inference pipelines to optimize KV cache management and memory scheduling.
• Lead research efforts and translate insights into production-grade systems.

Skills

C/C++

Python

Education

Bachelor's or Master's in CS/EE (PhD preferred)

Tools

vLLM

Ray Serve

TensorRT-LLM

Job description

European Tech Recruit is assisting a leading telecommunications company in Edinburgh to hire a Systems Research Engineer focused on AI infrastructure and C++ systems engineering. You will help build scalable distributed architectures and contribute to a world-class research program in a dynamic data-center setting.

The ideal candidate has a CS/EE degree (PhD preferred), strong C/C++ skills, Python for prototyping, and hands-on experience with LLM serving tools such as vLLM and Ray Serve.