Senior DevOps Engineer - AI and Cloud InfrastructureType: Permanent / Full-Time (Employment or Contract considered)Location: Remote or HybridTime Zones: UK, Europe, North America-friendlyThe OpportunityWe''re working with a high-growth tech-start up company building a next-generation AI cloud platform, focused on fast, reliable inference for large language models and other compute-intensive workloads.The platform combines modern cloud infrastructure, Kubernetes, GPU clusters, and developer-first tooling to support mission-critical AI systems operating across multiple regions.They''re now looking for a Senior DevOps Engineer to take ownership of the infrastructure backbone - someone who enjoys operating complex systems at scale and working closely with infrastructure, ML, and product engineering teams.What You''ll Be DoingAI Cloud InfrastructureDesign, build, and operate highly available, secure infrastructure supporting AI inference, fine-tuning, and data processing workloadsManage multi-region Kubernetes clusters, including GPU-heavy environmentsImplement autoscaling strategies across heterogeneous compute fleetsInfrastructure as Code and AutomationOwn and evolve infrastructure-as-code using tools such as Terraform, Helm, and similarAutomate provisioning of compute, networking, and storageBuild tooling to spin environments up and down for experiments, benchmarks, and customer deploymentsCI/CD and Release EngineeringDesign and maintain CI/CD pipelines across backend, infrastr