AI Platform Engineer ,OpenShift / NVIDIA (Freelance) (Remote)

AI Platform Engineer, OpenShift / NVIDIA (Freelance) Positions: 1 Experience: Ideally 6-10 years. Mission Own deployment and operation of the underlying enterprise AI/model-serving platform. Mandatory capabilities Kubernetes Red Hat OpenShift Containers/Docker/OCI Helm Linux CI/CD GitOps Networking Secrets/certificates Registries Monitoring/observability Priority AI infrastructure experience OpenShift AI KServe NVIDIA GPU Operator NVIDIA NIM NVIDIA AI Enterprise GPU inference Open-weight LLM deployment vLLM or comparable serving engines GPU monitoring and performance optimization Candidates should understand practical inference concepts including tokens/sec, TTFT, prefill vs decode, context length, KV cache, prefix caching, batching, concurrency, GPU memory, quantization and model routing .