LLM Interview Questions

The Model Context Protocol is Anthropic's open standard reshaping how LLMs connect to tools and data. If you're interviewing for Claude ecosystem roles or AI platform engineering, expect MCP questions. Understand host vs server architecture and how MCP differs from ad-hoc function calling.

Structured JSON output from LLMs is a production necessity at Stripe, Vercel, and every AI-native startup. Interviewers test your reliability engineering — schema enforcement, retry logic, streaming edge cases — not just 'use JSON mode.' Master the full production playbook.

Self-hosting Llama 3 is a infrastructure-heavy question for ML platform and AI engineer roles at Meta-adjacent companies. Expect deep dives on quantization, vLLM, GPU sizing, and the TCO math that determines build vs buy decisions.

Advanced scenario question on why LLMs hallucinate — next-token prediction vs fact verification, root causes, and production defenses asked at OpenAI, Google, Meta, Anthropic, Microsoft, and Amazon.

LLM interview topic on distillation — teacher/student training, latency/cost wins, and quality regression risks.

**Training** Refusal datasets, toxicity filters on training data.

**Eval design** Expert-labeled scenarios; citation accuracy checks; refusal appropriateness.

**Eval dimensions** SWE-bench-style tasks on private repo sample; CI fix rate; hallucinated APIs.

**Structure** Eval templates + data JSONL + scoring functions; CI integration via API.

Conceptual Transformer interview answer — self-attention, encoder-decoder vs decoder-only, and why parallel training beat RNNs for language modeling.

RAG has become the foundational architecture for production GenAI applications at companies like Notion, Duolingo, and Morgan Stanley. Interviewers expect you to explain the full retrieval pipeline — not just define the acronym. Follow along to master what RAG is, when to use it over fine-tuning, and how to articulate trade-offs that separate junior from senior candidates.

AI Agents are the hottest topic in 2025–2026 GenAI interviews, but most candidates confuse agents with chatbots. Interviewers at OpenAI and Anthropic want you to articulate the agent loop — perceive, plan, act, reflect — and explain when tool use justifies agent complexity over a simple chain.

Multi-agent orchestration is a senior/staff-level system design question gaining traction at Google DeepMind and Microsoft. Learn the supervisor pattern, shared state management, and how to avoid the 'too many agents' anti-pattern that sinks most candidate answers.

Chain-of-Thought prompting remains one of the most frequently asked prompt engineering questions, yet candidates often give surface-level answers. Learn when CoT helps vs hurts, production token costs, and advanced variants like self-consistency and tree-of-thoughts that impress senior interviewers.

OpenAI's model lineup changes fast. GPT-4 vs GPT-4o is a model selection question that tests whether you understand latency, cost, multimodal capabilities, and when reasoning depth matters. Critical for any role touching OpenAI APIs in production.

Constitutional AI is Anthropic's differentiator and a must-know for Claude-focused interviews. Go beyond the marketing — explain the self-critique training loop, how CAI compares to RLHF, and practical safety implications for production deployments.

Claude Code is Anthropic's CLI coding agent designed for repository-level work: reading the codebase, editing multiple files, running tests/builds, and iterating until a task succeeds. Unlike autocomplete-first copilots that live inside the editor, Claude Code operates as an agent loop — observe → plan → act (edit/run tools) → verify.

A production Claude Code rollout is an agent platform problem, not a 'give everyone a CLI' problem.

Codex CLI represents OpenAI's push into agentic coding outside the editor — similar category to Claude Code and other CLI agents. The core loop is: understand task → explore repo → edit → run commands → iterate.

Cost optimization for coding agents is context engineering + runtime policy.

A production AI coding agent typically includes:

AI observability extends classic APM.

Treat agent models/prompts/tools like dependencies.

Part 2 of the LLM hallucination handbook — factual, citation, reasoning, math, code, temporal, context, and tool-use hallucinations; decoding risks; RAG failure modes; production case study.