Systems Research Engineer - Distributed Systems​/C++

We are currently partnered with a globally leading research centre in the UK looking to expand their team with a Systems Research Engineer. This is an incredibly high calibre team reshaping how large-scale models are trained and served through next-generation AI-native infrastructure and "super-node" clusters.

This is a permanent opportunity based onsite in Edinburgh.

• Architect and implement distributed system components for AI workloads across CPU, GPU, and NPU clusters.
• Conduct in-depth profiling and performance tuning of inference pipelines, focusing on KV cache management.
• Develop low-latency, fault-tolerant AI serving frameworks using vLLM, Ray Serve, and PyTorch Distributed.
• Research and prototype novel techniques for cache sharing, data locality, and resource orchestration.
• Translate innovative designs into publishable contributions at top-tier venues (e.g., OSDI, NSDI, MLSys).
• Collaborate with global research teams to drive the internal adoption of novel system architectures.

• Preferably a PhD, at minimum a masters degree, in Computer Science, distributed systems, or related field.
• Strong knowledge of Distributed Systems, OS internals, and Machine Learning systems architecture.
• Hands-on experience with LLM serving frameworks (vLLM, Ray Serve, TensorRT-LLM, or TGI).
• Proficiency in C/C++ for systems development and Python for research prototyping.
• Solid grounding in distributed algorithms, load balancing, and state management.
• Proven ability to conduct systems research, ideally evidenced by publications in top-tier conferences.

/ Distributed Systems / AI Infrastructure / LLM Serving / vLLM / KV Cache / Performance Optimization / Machine Learning Systems / C++ / Python / Ray Serve / PyTorch Distributed / Cloud Infrastructure

By applying to this role you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice