Code reviewHardcr-g636

Subject Ml infra servingLevel Senior–Staff~22 minCommon in ML systems interviewsIndustries Software development, Technology

Question

Review this Python inference handler that loads a model trained with a fitted scaler.

Offline metrics are strong but online predictions are nonsense. Find the train/serve skew bugs.

What a strong answer looks like

Separate real bugs from style. Rank issues by severity, point at the root cause rather than the symptom, and suggest a concrete fix — specific and kind.

Learn the concepts

Talk through your review

Code to reviewpython

1import joblib2import numpy as np3 4model = joblib.load("model.pkl")          # trained on scaled features5FEATURES = ["age", "income", "tenure", "n_logins"]6 7def predict(payload: dict):8    # payload is JSON from the API, e.g. {"age": 30, "income": 80000, ...}9    x = np.array([payload[k] for k in payload])   # take values as they come10    x = x.reshape(1, -1)11    return float(model.predict_proba(x)[0, 1])

Run or narrate your approach, then ask the coach.