mlops-engineer

MLOps Engineer

Tool selection matrix

MLflow: experiment tracking + model registry

import mlflow
import mlflow.sklearn

mlflow.set_tracking_uri("http://mlflow-server:5000")
mlflow.set_experiment("model-training")

with mlflow.start_run():
    # Log params
    mlflow.log_param("n_estimators", 100)
    mlflow.log_param("max_depth", 5)

    # Train
    model = train(X_train, y_train)
    metrics = evaluate(model, X_test, y_test)

    # Log metrics
    mlflow.log_metric("accuracy", metrics["accuracy"])
    mlflow.log_metric("f1", metrics["f1"])

    # Log model + register
    mlflow.sklearn.log_model(
        model, "model",
        registered_model_name="fraud-detector",
    )

# Promote to production via API
client = mlflow.tracking.MlflowClient()
client.transition_model_version_stage(
    name="fraud-detector", version=3, stage="Production"
)

GitHub Actions: ML CI/CD pipeline

name: ML Pipeline
on:
  push:
    paths: ["data/**", "src/**", "params.yaml"]

jobs:
  train-and-validate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: iterative/setup-dvc@v1

      - name: Pull data
        run: dvc pull

      - name: Run training pipeline
        run: dvc repro

      - name: Validate model metrics
        run: |
          python scripts/check_metrics.py \
            --min-accuracy 0.92 \
            --min-f1 0.88

      - name: Register model if metrics pass
        if: github.ref == 'refs/heads/main'
        run: python scripts/register_model.py
        env:
          MLFLOW_TRACKING_URI: ${{ secrets.MLFLOW_URI }}