AI Platform Engineer with Kubernetes

As a Senior AI Platform Engineer, you will own the infrastructure powering production AI workloads across cloud and on-prem environments. You'll build scalable, secure, and reliable AI platforms while working closely with engineering teams to enable high-quality AI products.This is a long-term, full-time remote engagement. Main responsibilitiesBuild and maintain AI infrastructure on KubernetesDesign and operate production model serving and inference platformsDevelop AI platform services, deployment workflows, and automationImprove observability, monitoring, evaluation, and platform reliabilityImplement security, governance, and compliance best practicesOptimize AI infrastructure performance and operational costsContribute to Python services supporting the platformCollaborate with engineering teams on architecture and platform improvements Requirements5+ years of experience in Platform Engineering, DevOps, SRE, or Infrastructure EngineeringStrong Kubernetes experience, including GPU workloadsExperience with cloud-native infrastructure and Infrastructure as CodeHands-on experience serving LLMs or production AI workloadsExperience with RAG infrastructure, vector databases, or AI platform componentsStrong Python development skillsExperience with monitoring, observability, and CI/CD pipelinesStrong understanding of security, compliance, and production best practicesExcellent communication skills in EnglishAbility to work independently and take ownership Nice to haveExperience with vLLM, KServe, LiteLLM, Langfuse, or MLflowExperience supporting SaaS, private cloud, or on-prem deploymentsExperience with multi-tenant platformsFamiliarity with GDPR, ISO 27001, or enterprise complianceExperience optimizing AI infrastructure costsExperience building internal developer platforms