Writing
learning is continuous, documenting is sporadic.
- 2026-07-25
NGBoost: When a Number Isn't Enough
Standard gradient boosting gives you a prediction. NGBoost gives you a probability distribution. Here's why that distinction changes how you build ML systems.
mlopsml-engineeringngboost - 2025-07-01
Building a Feature Store for MLB Predictions
How I designed a lightweight feature store on S3 to serve real-time batter and pitcher stats to a SageMaker endpoint.
mlopsawssystems