Resume/Projects/Cloud + Kubernetes AI Deployment Platform
Live deployment platform

Cloud + Kubernetes AI Deployment Platform

Deployment-platform project that runs the completed black-box distillation API behind an observability gateway, adds Docker Compose and Kubernetes manifests, readiness/liveness probes, CI validation, Prometheus metrics, Grafana dashboards, and a cloud-ready GKE path.

Send a prediction through the Kubernetes-ready gateway and inspect workload health, metrics, and deployment targets.

Kubernetes
Docker
FastAPI
Prometheus
Grafana
Send platform prediction

Page expectations

What this route loads and what you should see.

Data source

Loads gateway status, upstream health, metrics contract, and deployment targets.

Expected result

Returns the black-box student prediction through the platform gateway while recording request and prediction metrics.

Kubernetes-ready prediction

Send a prediction through the Kubernetes-ready gateway and inspect workload health, metrics, and deployment targets.

Returns the black-box student prediction through the platform gateway while recording request and prediction metrics.

Use at least 40 characters so the model has context.

Gateway status

Loads gateway status, upstream health, metrics contract, and deployment targets.

Loading deployment platform status.

Platform prediction

Returns the black-box student prediction through the platform gateway while recording request and prediction metrics.

Submit the form to see the prediction here.

Grafana dashboard

Rendered preview of the Grafana dashboard provisioned with the deployed platform.

Grafana dashboard

Cloud Kubernetes AI Platform

Last 1h ยท refresh 30s

Request rate by status

timeseries

Separates gateway request volume by HTTP status code.

Metric: ai_platform_requests_total

p95 gateway latency

timeseries

Tracks the 95th percentile gateway latency over the last five minutes.

Metric: ai_platform_request_latency_seconds_bucket

Upstream error rate

timeseries

Highlights timeout, invalid-response, and upstream failure modes.

Metric: ai_platform_upstream_errors_total

Prediction distribution

piechart
  • AI Engineer
  • Data Scientist
  • Sr. Data Scientist

Shows which student labels the live prediction path is returning.

Metric: ai_platform_predictions_total
Provisioned source

The live Grafana UI stays internal. This rendered preview is based on the committed dashboard definition at monitoring/grafana/dashboards/cloud-kubernetes-ai-platform.json.