Test-Time Training: When Your Model Learns During Inference
Test-time training lets models update their own weights during inference. Learn how TTT layers work, their GPU implications, and why this changes AI infrastructure.
Read Full Article →Blog
Notes from an AI systems engineer. Tutorials, deep dives, and honest reflections on progressing from data pipelines to GPU kernels.
LLM Observability: Tracing Your AI Applications
Learn how to add observability to LLM applications using OpenTelemetry and data engineering practices.
Read Full Article →Choosing a Vector Database: A Data Engineer's Guide
Compare ChromaDB, Pinecone, Weaviate, and pgvector to find the right vector database for your RAG application.
Read Full Article →Building a Production RAG Pipeline with Apache Airflow
Learn how to orchestrate a Retrieval-Augmented Generation pipeline using Apache Airflow and data engineering best practices.
Read Full Article →Prompt Version Control: Treating Prompts Like Production Code
Learn how to apply data engineering principles to manage LLM prompts with versioning, labels, and rollback capabilities.
Read Full Article →Causality is the Missing Piece in Modern AI
Most ML models find patterns in data but can't answer 'why'. I explain why understanding causality matters for building intelligent systems, especially in robotics and reinforcement learning.
Read Full Article →RAG is Just ETL with Extra Steps: A Data Engineering Perspective
RAG isn't magic - it's Extract, Transform, Load with vectors. I break down how your existing pipeline skills map directly to building production AI systems.
Read Full Article →Why Data Engineers Should Learn AI (And How I'm Doing It)
As a data engineer transitioning into AI, I share why this path makes sense, what advantages we have, and my learning roadmap.
Read Full Article →LAUNCHING MARCH 2026
Build an AI Agent in 5 Days
10 minutes a day. 5 days. One working AI agent. Join the waitlist — launching first week of March.
No spam. Unsubscribe anytime.