ml-engineering

name	ml-engineering
description	ML pipeline design, feature engineering, model training/serving, experiment tracking, model validation, and MLOps principles.

ML Engineering Principles

Guidelines for building reliable, reproducible machine learning systems.

When to Invoke

• Designing ML pipelines (training, serving)
• Feature engineering and data preparation
• Model evaluation and validation
• MLOps infrastructure decisions

ML Pipeline Design

Stages

Data Collection → Feature Engineering → Training → Evaluation → Deployment → Monitoring

Principles

1. Reproducibility — versioned data, code, and config. Same inputs = same model.
2. Experiment tracking — every run logged (MLflow, W&B, Neptune).
3. Feature stores — centralized feature computation, reusable across models.
4. Model registry — versioned models with metadata, promotion workflow.

Feature Engineering

1. Compute features once, reuse everywhere — feature store pattern.
2. Training-serving skew prevention — same transformation code in training and inference.
3. Feature documentation — every feature has description, source, freshness requirement.

Model Validation

Checklist

• Performance metrics meet threshold (accuracy, F1, AUC, etc.)
• No data leakage (target info in features)
• Fairness evaluation across protected groups
• Performance on edge cases and out-of-distribution data