Systems Research Engineer - Distributed Systems / C++

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.

Key responsibilities for this Systems Research Engineer position:

• 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 r...