ML Ops Engineer

# model_server.py -- FastAPI model serving
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
import mlflow.pyfunc, time

app = FastAPI()
model = mlflow.pyfunc.load_model("models:/fraud_detector/Production")

class PredictionRequest(BaseModel):
    features: list[float]

class PredictionResponse(BaseModel):
    prediction: float
    model_version: str
    latency_ms: float

@app.post("/predict", response_model=PredictionResponse)
async def predict(req: PredictionRequest):
    start = time.time()
    try:
        pred = model.predict([req.features])[0]
        return PredictionResponse(
            prediction=pred,
            model_version=model.metadata.run_id,
            latency_ms=(time.time() - start) * 1000,
        )
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.get("/health")
async def health():
    return {"status": "healthy", "model_loaded": model is not None}

# k8s/model-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: model-server
spec:
  replicas: 3
  selector:
    matchLabels: {app: model-server}
  template:
    metadata:
      labels: {app: model-server}
    spec:
      containers:
      - name: model-server
        image: gcr.io/project/model-server:v1.2.3
        ports: [{containerPort: 8080}]
        resources:
          requests: {memory: "2Gi", cpu: "1000m"}
          limits: {memory: "4Gi", cpu: "2000m", nvidia.com/gpu: 1}
        env:
        - {name: MODEL_URI, value: "s3://models/production/v1.2.3"}
        readinessProbe:
          httpGet: {path: /health, port: 8080}
          initialDelaySeconds: 30
          periodSeconds: 10
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: model-server-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: model-server
  minReplicas: 2
  maxReplicas: 10
  metrics:
  - type: Resource
    resource:
      name: cpu
      target: {type: Utilization, averageUtilization: 70}

# monitoring/drift_detector.py
import numpy as np
from scipy import stats
from dataclasses import dataclass

@dataclass
class DriftResult:
    feature: str
    drift_score: float
    is_drifted: bool
    p_value: float

def detect_drift(reference: np.ndarray, current: np.ndarray, threshold: float = 0.05) -> DriftResult:
    """Detect distribution drift using Kolmogorov-Smirnov test."""
    statistic, p_value = stats.ks_2samp(reference, current)
    return DriftResult(feature="", drift_score=statistic, is_drifted=p_value < threshold, p_value=p_value)

def monitor_all_features(reference: dict, current: dict, threshold: float = 0.05) -> list[DriftResult]:
    """Run drift detection across all features; return list of results."""
    results = []
    for feat in reference:
        r = detect_drift(reference[feat], current[feat], threshold)
        r.feature = feat
        results.append(r)
    return results

ALERT_RULES = {
    "latency_p99":    {"threshold": 200,  "severity": "warning",  "msg": "P99 latency exceeded 200 ms"},
    "error_rate":     {"threshold": 0.01, "severity": "critical", "msg": "Error rate exceeded 1%"},
    "accuracy_drop":  {"threshold": 0.05, "severity": "critical", "msg": "Accuracy dropped > 5%"},
    "drift_score":    {"threshold": 0.15, "severity": "warning",  "msg": "Feature drift detected"},
}

# features/customer_features.py
from feast import Entity, Feature, FeatureView, FileSource, ValueType
from datetime import timedelta

customer = Entity(name="customer_id", value_type=ValueType.INT64)

customer_stats = FeatureView(
    name="customer_stats",
    entities=["customer_id"],
    ttl=timedelta(days=1),
    features=[
        Feature(name="total_purchases",       dtype=ValueType.FLOAT),
        Feature(name="avg_order_value",        dtype=ValueType.FLOAT),
        Feature(name="days_since_last_order",  dtype=ValueType.INT32),
        Feature(name="lifetime_value",         dtype=ValueType.FLOAT),
    ],
    online=True,
    source=FileSource(
        path="gs://features/customer_stats.parquet",
        timestamp_field="event_timestamp",
    ),
)

from feast import FeatureStore
store = FeatureStore(repo_path=".")
features = store.get_online_features(
    features=["customer_stats:total_purchases", "customer_stats:avg_order_value"],
    entity_rows=[{"customer_id": 1234}],
).to_dict()

import mlflow

mlflow.set_tracking_uri("http://mlflow.company.com")
mlflow.set_experiment("fraud_detection")

with mlflow.start_run(run_name="xgboost_v2"):
    mlflow.log_params({"n_estimators": 100, "max_depth": 6, "learning_rate": 0.1})
    model = train_model(X_train, y_train)
    mlflow.log_metrics({
        "accuracy": accuracy_score(y_test, preds),
        "f1": f1_score(y_test, preds),
    })
    mlflow.sklearn.log_model(model, "model", registered_model_name="fraud_detector")

python scripts/model_registry.py register --name fraud_detector --version v2.3 --metrics '{"f1":0.91,"auc":0.95}' --params '{"n_estimators":200}'
python scripts/model_registry.py promote --name fraud_detector --version v2.3 --stage production
python scripts/model_registry.py list --stage production --json
python scripts/model_registry.py compare --name fraud_detector --versions v2.2 v2.3
python scripts/drift_detector.py --reference train_data.csv --current prod_data.csv
python scripts/drift_detector.py --reference baseline.csv --current latest.csv --threshold 0.1 --json
python scripts/pipeline_validator.py --pipeline pipeline.json --strict
python scripts/pipeline_validator.py --pipeline pipeline.json --json