Design build and operate secure scalable GCP and OpenShift (OCP/GKE) platforms to support deployment of GenAI models LLMs and RAG workloads.
Provision and manage cloud infrastructure using Terraform including landing zones networking org policies and hybrid connectivity across GCP and Azure.
Enable MLOps/LLMOps pipelines for model deployment monitoring and lifecycle management integrating Arize AI and GenAI platforms.
Implement platform engineering best practices including Kubernetes-based abstractions internal developer portals and self-service environments.
Ensure platform security governance and secrets management using HashiCorp Vault IAM and policy-as-code.
Establish observability SLOs and SRE practices to ensure reliability and performance of GenAI and platform services.
Collaborate with data scientists ML engineers and application teams to onboard new LLMs APIs and inference services efficiently.
Cloud Platform Engineer Location: Charlotte NC Type of Hire: C2C positions :: 2 Key Skills: Must-Have Skills (Mandatory): GCP Azure (multi-cloud preferred) Terraform (strong hands-on IaC) Cloud Networking & Hybrid Connectivity (VPN VPC/VNet peering private endpoints) Landing Zones & Cl...
Design build and operate secure scalable GCP and OpenShift (OCP/GKE) platforms to support deployment of GenAI models LLMs and RAG workloads.
Provision and manage cloud infrastructure using Terraform including landing zones networking org policies and hybrid connectivity across GCP and Azure.
Enable MLOps/LLMOps pipelines for model deployment monitoring and lifecycle management integrating Arize AI and GenAI platforms.
Implement platform engineering best practices including Kubernetes-based abstractions internal developer portals and self-service environments.
Ensure platform security governance and secrets management using HashiCorp Vault IAM and policy-as-code.
Establish observability SLOs and SRE practices to ensure reliability and performance of GenAI and platform services.
Collaborate with data scientists ML engineers and application teams to onboard new LLMs APIs and inference services efficiently.