Chunking Interview Questions

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.

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 ops question on index versioning, dual-write, and blue-green cutovers.

**Use cases** Full codebase questions, hours-long media, multi-doc merger analysis.

**Fit** Nightly evals, backfill embeddings, document tagging — not interactive chat.

Field selection, normalization, ACL tags, temporal fields, and schema evolution without breaking filters.

Shared embedding spaces, separate indexes, CLIP-style models, metadata routing, and fusion strategies.

Hard RAG interview question on late chunking and contextual retrieval — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on parent-child and hierarchical chunking — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on chunking strategies for different document types — architecture, trade-offs, eval, and production patterns.

Scenario question on cross-model tokenizer bugs — chunk boundaries, context overflow, and embedder vs LLM alignment.

Hallucination in RAG systems is the #1 production failure mode cited in AI engineering interviews. Your interviewer wants a systematic debugging framework — not a list of buzzwords. Learn how to measure faithfulness, fix retrieval precision, and layer mitigations the way senior engineers at Databricks and Meta actually ship RAG.

**Ingestion** OCR for scans; preserve tables; metadata for citations.

**Strategies** Full dump only when eval proves benefit; otherwise RAG + selective long paste.

BM25 + vector fusion, RRF, weighted scores, rerankers, and same-chunk alignment pitfalls.

Snapshot strategies, embedding model lineage, cross-region restore, and rebuild-from-source playbooks.

Hard context engineering trade-offs: prioritization tiers, dynamic reallocation, and what to drop first under pressure.

Schema-first extraction from PDFs, emails, and contracts with validation, chunking, and merge strategies.

Context budget tactics: summarization, selective retrieval, example pruning, and distillation for long-running agent sessions.

Medium RAG interview question on end-to-end rag observability — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on cost of embeddings at 100m documents — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on compression and contextual distillation — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on small-to-big retrieval patterns — architecture, trade-offs, eval, and production patterns.

Medium RAG interview question on when rag fails: debugging playbook — architecture, trade-offs, eval, and production patterns.