1 of 1 Ray Jobs in Edinburgh

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 … 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 ...