A collection of technical writing across AI engineering, machine learning, systems, graph analysis, and core computer science topics. I use writing to clarify how I think through technical problems and explain ideas in a structured, practical way.
Selected posts that reflect both my current AI engineering direction and earlier technical foundations.
AI Engineering / RAG / Agentic Workflows
A breakdown of how I designed a multi-agent workflow for search, retrieval, synthesis, and evaluation, and what building it taught me about grounded AI systems, modularity, and retrieval quality.
Machine Learning / Model Evaluation
A reflection on why accuracy alone can be misleading in healthcare-style prediction problems, and how choosing better evaluation metrics can change model decisions and practical usefulness.
Graph Analysis / Data Exploration
An exploration of Twitch-related data through graph-based analysis using Neo4j, showing how relationships and graph structure can reveal insights beyond flat-table analysis.
Systems / Computer Architecture
A technical note on NUMA architecture and why memory locality matters for system performance, especially in modern multi-processor computing environments.
Algorithms / Core Computer Science
An accessible explanation of negative weight cycles and the Bellman-Ford algorithm, focused on building intuition as well as algorithmic understanding.
Writing helps me sharpen both technical understanding and communication.
A mix of current AI engineering interests and broader technical foundations.