Architecture

The image below shows users from two tenants (Coke and Pepsi Rafay Orgs) securely deploying and using serverless pods on a service provider's datacenter.

---

This architecture illustrates the two key personas and their workflows:

• End Users launch serverless pods by selecting a profile, specifying minimal configuration (CPU/GPU), and starting workloads such as Jupyter notebooks or inference services.
• Rafay Platform automates pod provisioning, monitoring, and lifecycle management on Kubernetes clusters, with built-in scale-to-zero and per-use billing.

sequenceDiagram
    participant User as End User
    participant Hub as Developer Hub
    participant Ctrl as Controller
    participant K8s as K8s Cluster
    participant Pod as Serverless Pod

    User->>Hub: Login
    Hub-->>User: Dashboard
    User->>Hub: Select "Serverless Pods"
    User->>Hub: Configure Pod (CPU/GPU, Profile, SSH)
    User->>Hub: Click "Launch"
    Hub->>Ctrl: Request Pod Provisioning
    Ctrl->>K8s: Schedule Pod with profile
    Ctrl->>K8s: Create SSH Secret & Service
    K8s->>Pod: Start container (Jupyter/Inference/Custom)
    Pod-->>User: Access URL (Jupyter/Shell/Service)
    Pod-->>User: SSH Credentials & Command
    User->>Pod: Connect via SSH
    Note over Pod: Idle pods auto scale-to-zero
    Pod->>Ctrl: Send Metrics (GPU/CPU/Memory)
    Ctrl-->>Hub: Real-time Monitoring

---