2 of 2 Amazon SageMaker Jobs in Scotland

including model hosting, request routing, continuous batching, and KV-cache optimization \n Deploy, host, and lifecycle-manage open-source and proprietary LLMs on Amazon EKS and Amazon SageMaker, as well as on-prem and local GPU clusters, using reproducible infrastructure as code and continuous delivery pipelines … operating LLM inference servers such as vLLM and llm-d (or directly equivalent serving stacks) \n Hands-on experience hosting and serving LLMs on Amazon EKS and/or Amazon SageMaker, and on local GPU infrastructure \n Knowledge of LLM reliability and risk considerations, including latency/ ...

agnostic engineering mindset; able to work across varied client stacks. Experience with cloud AI services and MLOps/LLMOps (e.g., Azure AI Foundry, AWS SageMaker and/or Bedrock). Strong software engineering practices: Python, APIs, containerisation, CI/CD, IaC, testing, observability and production support. Modern ML/ ...