MLOpsCI/CD

CI/CD for ML Models

Automated training, evaluation, and deployment with GitHub Actions and SageMaker.

May 20, 20241 min read

ML models need the same deployment rigor as application code. Here's how we built an automated pipeline with GitHub Actions triggering SageMaker training jobs, evaluation gates, and canary deployments.

Why I Still Reach for Boring Python FirstI default to stdlib and dataclasses until complexity is earned. Here is the heuristic I use to decide when a framework is worth the overhead.3 min read

PythonOpinionEngineering

Evals Are the ProductWhy treating evaluations as a first-class product concern is the difference between shipping reliable LLM applications and guessing.4 min read

AITesting

Building a Design System from ScratchLessons learned creating a token-based design system with Tailwind v4.1 min read

Design SystemsTailwind

Stay in the loop

New posts on engineering, architecture, and what I'm building.