●Blog · 15 posts
AI engineering, explained simply.
Notes from preparing for an AI Technical Manager interview: every question I expected, answered the way I'd say it out loud, with the architecture behind it.
01Start here
The full interview guide, on one page.

AI Technical Manager interview: 15 questions and how I answer them
The questions an AI Technical Manager interview is likely to ask about MCP, agents, RAG, evals, vibe coding, cost, multi-tenancy and team leadership, with plain-English answers and architecture diagrams.
2 min read · Read the guide →02AI basics
Two concepts worth getting right.
2 min readWhat is an AI hallucination, and how do you stop it?
A plain-English explanation of AI hallucinations: why LLMs confidently make things up, and the three things I do in production to stop it: grounding, citations and an "I don't know" threshold.
2 min readWhat is an event loop? The waiter explanation, for FastAPI and Node
An event loop explained with a restaurant waiter: how FastAPI and Node.js serve hundreds of LLM requests on one thread, and why one blocking call inside an async route freezes everyone.
03Interview questions
Twelve questions, answered plainly.
MCP, agents, RAG, evals, vibe coding, cost, multi-tenancy and leadership. Each post has a diagram and the short version to say out loud.
2 min readQ1. How do you design an MCP server: tools, resources or prompts?
How I design Model Context Protocol (MCP) servers for enterprise systems: deciding between tools, resources and prompts by who is in control, using Streamable HTTP, and filtering tools so the model never sees 100 at once.
2 min readQ2. How do you secure MCP servers?
Securing Model Context Protocol servers in an enterprise: OAuth 2.1 with audience checks, no token passthrough, scoped downstream credentials, treating tool output as untrusted, and human approval for risky actions.
2 min readQ3. Simple workflow or autonomous multi-agent system?
When to use a single LLM call, a deterministic workflow, an agent graph or a multi-agent system, and the guardrails (step limits, token budgets, checkpoints, human handoff) that keep agents from running away.
2 min readQ4. Your RAG system is slow and makes things up. How do you fix it?
How I fix a RAG pipeline that is slow and hallucinates: hybrid vector and keyword search, tenant pre-filtering, reranking, Redis caching, citations and an abstain threshold.
2 min readQ5. How do you test and monitor AI in production?
A practical setup for AI evaluation: a golden test set run on every change, shadow and canary rollouts, and production signals like time to first token, cost per session and how often users edit AI output.
2 min readQ6. How do you let teams vibe code without wrecking code quality?
How I roll out AI coding assistants to an engineering team: shared repo rules, tests first, security scanning in CI with tools like Vibefort, and the rule that the engineer owns every line they merge.
2 min readQ7. How do you keep LLM cost and latency low as traffic grows?
Three levers for LLM unit economics in a SaaS product: route easy tasks to small models, cache with prompt caching and Redis, and stream responses from FastAPI while pushing post-processing to a queue.
2 min readQ8. How do you make sure customer A never sees customer B's data?
Tenant isolation for AI backends in Python and TypeScript: tenant_id from verified auth, Postgres row-level security, pre-filtered vector search, namespaced Redis keys, and never letting the LLM choose the tenant.
2 min readQ9. How do you turn full-stack developers into AI engineers?
How I grow backend and frontend developers into AI engineers: a ready starter template, a step-by-step path from structured output to RAG, agents and MCP, and a weekly review of real failures.
2 min readQ10. Product wants autonomous agents, Sales wants a demo next week. What do you do?
How I handle competing pressure from Product and Sales on an AI agent feature: a guided flow with human approval in two weeks, evals from real usage next, and autonomy only where accuracy proves it.
2 min readQ11. Tell me about an AI system you built and the value it created
Two AI systems I architected end to end: ResolveOps, an AI billing-support agent with cited investigations and human-approved refunds, and the Actionable HQ commitment engine with WhatsApp follow-ups for 10,000+ users.
2 min readQ12. What do you look for when hiring AI engineers?
What I test for when hiring AI engineers: software fundamentals, structured debugging of real AI failures, and product sense about cost, speed and what happens when the AI is wrong.