Backend Pe Python Ml

Principal-engineer-grade Python ML backend design, implementation, and review - training pipelines, inference services, feature stores, and MLOps. Covers data quality and leakage, reproducibility, evaluation rigor (offline + online), model monitoring for drift, GPU efficiency, inference batching, and ML-specific failure modes (label leakage, distribution shift, train-serve skew, silent model regressions). Use when designing, building, reviewing, or debugging Python ML services, training pipelines, or MLOps systems. Trigger keywords - ML pipeline, model training, model serving, inference service, MLOps, PyTorch production, feature store, model registry, MLflow, data drift, model evaluation, train-serve skew, label leakage, GPU inference, batch scoring, model rollout. Not for generic Python backend work (use backend-pe-python).

praxstack Updated 1 repo stars

File contents

praxstack/skills-and-personas commit 3e376027fd

Frequently asked questions

npx get-skill add praxstack/backend-pe-python-ml