| 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
- Reproducibility — versioned data, code, and config. Same inputs = same model.
- Experiment tracking — every run logged (MLflow, W&B, Neptune).
- Feature stores — centralized feature computation, reusable across models.
- Model registry — versioned models with metadata, promotion workflow.
Feature Engineering
- Compute features once, reuse everywhere — feature store pattern.
- Training-serving skew prevention — same transformation code in training and inference.
- Feature documentation — every feature has description, source, freshness requirement.
Model Validation
Checklist
Model Serving
| Pattern | When |
|---|
| Batch inference | Scheduled predictions, large volumes, latency-tolerant |
| Real-time API | Low-latency, per-request predictions |
| Streaming | Continuous predictions on event streams |
| Edge | On-device, offline-capable |
Monitoring
- Data drift detection — statistical tests on input distributions.
- Model performance monitoring — track prediction accuracy over time.
- Feature importance drift — alert when feature contributions shift.
- Automated retraining triggers — retrain when performance degrades below threshold.
Tools Ecosystem
| Category | Tools |
|---|
| Experiment tracking | MLflow, Weights & Biases, Neptune |
| Feature stores | Feast, Tecton, Hopsworks |
| Model registry | MLflow, Vertex AI, SageMaker |
| Data versioning | DVC, LakeFS |
| Pipeline orchestration | Kubeflow, Vertex AI Pipelines, Airflow |
Related
- Data Engineering @.agents/skills/data-engineering/SKILL.md
- Python Idioms @.agents/skills/python-idioms/SKILL.md
- Performance Optimization Principles @.agents/rules/performance-optimization-principles.md
