Systems Research Engineer, AI Infrastructure (C++/Python)

European Tech Recruit; Livingston; On-site; GBP 70,000 - 120,000; Full time

Job summary

European Tech Recruit in Edinburgh is seeking a Systems Research Engineer to help scale AI infrastructure and redefine the foundational software stack for the LLM era.

You will tackle distributed systems bottlenecks, perform in-depth profiling of large-scale inference pipelines, and optimize AI serving frameworks to achieve low-latency, multi-tenant performance. This role offers collaboration with senior researchers and potential for publications.

Qualifications

• Bachelor's or Master's in CS/EE or related field (PhD highly preferred).
• Strong proficiency in C/C++ for systems work, with Python for rapid prototyping.
• Hands-on experience with LLM serving frameworks (vLLM, Ray Serve, TensorRT-LLM) and distributed algorithms.
• Solid grounding in systems research methodology and performance profiling tools.

Responsibilities

• Research and develop scalable distributed system components for AI infrastructure.
• Profile and optimize large-scale inference pipelines focusing on KV cache management.
• Contribute to AI serving frameworks and publish findings at top venues.
• Collaborate with senior researchers to translate ideas into production-ready solutions.

Skills

C/C++

Python

LLM serving

Distributed systems

Performance profiling

Education

Bachelor's or Master's in CS/EE

PhD preferred

Tools

vLLM

Ray Serve

TensorRT-LLM

Job description

European Tech Recruit in Edinburgh is seeking a Systems Research Engineer to help scale AI infrastructure and redefine the foundational software stack for the LLM era.

You will tackle distributed systems bottlenecks, perform in-depth profiling of large-scale inference pipelines, and optimize AI serving frameworks to achieve low-latency, multi-tenant performance. This role offers collaboration with senior researchers and potential for publications.