Fine-Tuning Interview Questions for 10 Years Experience

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

Part 3 of the hallucination handbook — production defense layers from retrieval and prompting through guardrails, citations, confidence scoring, eval frameworks, and enterprise architecture. Asked at OpenAI, Google, Meta, Anthropic, Microsoft, and Amazon.

Model-based interview on DPO vs RLHF — preference pairs, training simplicity, and production trade-offs.

**Decision** Try prompt + tools + RAG first; fine-tune if style/reliability gap persists and data exists.

Hard model question comparing CAI, RLHF (PPO), and DPO — data efficiency, stability, and production fine-tuning trade-offs.

Hard scenario on LLM cost control — token budgeting, routing, caching, batch APIs, and unit economics at millions of queries.

Model question on RLHF — SFT, reward model, PPO alignment, and how human preferences change helpfulness vs hallucination trade-offs.

Enterprise RAG interviews test system design at scale: ACL-aware retrieval, audit logging, and ingestion pipelines for millions of documents. This is a staff-level question appearing at Microsoft, Salesforce, and Fortune 500 AI teams. Walk through a complete architecture with security boundaries and operational concerns.

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.

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.

500M vectors at sub-100ms p99 is a staff-level vector search design question from Uber, Airbnb, and large-scale ML platform teams. Learn sharding strategies, index tuning, and the operational trade-offs that separate senior from principal engineers.

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

Cursor rules are context engineering in disguise.

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

This is an enterprise platform design question spanning agents, MCP, governance, and observability.

MCP multiplies agent power and attack surface.

Prompt injection is the #1 security interview topic for agents that read untrusted text.

Company-wide context is a platform product.

Repository configuration attacks target the files agents trust.

Governance is becoming the bottleneck — not model IQ.

Treat agent models/prompts/tools like dependencies.

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.

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.

Hard RAG pattern question on corrective retrieval and gated web fallbacks.