RAG · RETRIEVAL
RAG (Retrieval-Augmented Generation)
What RAG is, how it actually works in production, the trade-offs most teams miss, and how I approach retrieval quality in regulated enterprise systems.
READ TOPIC →ENGINEERING / A STRUCTURED KNOWLEDGE BASE
How I think,
written down.
Not encyclopedias. Each topic combines the concept, the trade-offs, the production considerations, and how I personally approach it after years of building these systems for a living.
AI & GENAI
Production AI, not demos.
AGENTIC AI · LANGGRAPH
Agentic AI
What agentic AI actually is beyond the hype — stateful workflows, tools, HITL gates — and how I design agent systems that survive production in regulated domains.
READ TOPIC →MCP · TOOLING
MCP (Model Context Protocol)
Why MCP matters as enterprise AI infrastructure — standardized tool surfaces, retrieval as a contract — and how I architected an MCP-based semantic retrieval platform.
READ TOPIC →EVALUATION · LLMOPS
LLM Evaluation
How to evaluate LLM systems like an engineer — golden sets, per-node metrics, regression gates — and why vibes-based quality is the most expensive mistake in AI engineering.
READ TOPIC →SYSTEM DESIGN
Systems that hold up.
CLOUD
Platforms that run.
SOFTWARE ENGINEERING
Craft that compounds.
INTERVIEW JOURNEY / PREPARATION & PERSPECTIVES
How I answer the hard questions.
PRINCIPAL · RAG · GENAI
RAG — Interview Perspective
How I approach RAG questions in senior AI engineering interviews — layered evaluation, honest trade-offs, and the production stories that matter.
READ PERSPECTIVE →