7 of 7 Low Latency Jobs in Scotland

using frameworks like vLLM, Ray Serve, and modern PyTorch Distributed systems. Scalable Model Serving Infrastructure : Develop and evaluate frameworks that enable efficient multi-tenant, low-latency, and fault-tolerant AI serving across distributed environments. Research and prototype new techniques for cache sharing, data locality, and resource orchestration ...

Europe. The Role Design, build and own end to end data pipelines supporting real time and batch analytics Work on high volume, low latency data use cases with a strong focus on reliability and scalability Develop production grade data solutions using software engineering best practices such ...

uncover performance bottlenecks and optimisation opportunities. Improve memory usage, caching strategies, and scheduling efficiency in large-scale inference systems. Create solutions that enable low-latency, multi-tenant AI services in distributed environments. Explore and prototype new approaches to inference architecture and cluster-level orchestration. Translate technical innovations into ...

inference pipelines Improve key-value cache efficiency and memory scheduling Identify bottlenecks and enhance system scalability using systematic performance analysis AI Serving Infrastructure Develop low-latency, multi-tenant, fault-tolerant model serving systems Work on areas such as cache sharing, data locality, and cluster scheduling Prototype and evaluate ...

performance tuning of large-scale inference pipelines, focusing on KV cache management and memory scheduling. Scalable Serving Infrastructure: Develop frameworks for multi-tenant, low-latency, and fault-tolerant AI serving, researching techniques for cache sharing and data locality. Research & Publications: Translate novel designs into publishable contributions for leading ...

Europe. The Role Design, build and own end to end data pipelines supporting real time and batch analytics Work on high volume, low latency data use cases with a strong focus on reliability and scalability Develop production grade data solutions using software engineering best practices such ...

pipelines, specifically focusing on KV cache management and heterogeneous memory scheduling. AI Serving: Optimising high-throughput frameworks (vLLM, Ray Serve, PyTorch Distributed) to ensure low-latency, multi-tenant performance. Research Leadership: Contributing to top-tier venues (OSDI, NSDI, EuroSys, MLSys) and driving those innovations into real-world production. ...