1 of 1 Storage Management Jobs in Oxfordshire

Lead SRE - AI

Location
Abingdon, England, United Kingdom
Docker and Kubernetes, including the ability to deploy and troubleshoot AI inference workloads. Public cloud experience with Azure and/or AWS, including compute, storage, networking, and managed AI services such as Azure OpenAI and SageMaker. Understanding of SRE/DevOps principles, including SLOs, error budgets, observability, incident management …/QLoRA) of open‐source LLMs for domain‐specific SRE tasks. Knowledge of petrotechnical, energy, or industrial IoT domains. Experience with identity and access management (Okta, VIDM, SSO/MFA) as it relates to securing AI APIs. Hands‐on scripting experience with Bash, PowerShell, or similar tools ...