Vector Database Interview Questions for 2 Years Experience

Vector databases power every RAG system, yet most candidates can't explain ANN algorithms or hybrid search. This fundamental question appears in 80% of AI engineering loops. Master dense vs sparse retrieval and when hybrid search wins.

Medium vector DB / embeddings trade-off question on dimensions vs cost/quality.

Latency, recall proxies, ingest lag, index size, filter rates, error budgets, and RAG downstream signals.

Pricing dimensions: vectors stored, dimensions, QPS, namespaces, egress, and when self-host breaks even.

PostgreSQL + pgvector tuning: HNSW vs IVFFlat, connection pooling, vacuum, partitioning, and when to outgrow Postgres.

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

Read replicas, eventual consistency after upserts, quorum writes, and RAG staleness expectations.

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

Brute-force exact search thresholds, ANN recall trade-offs, and hybrid exact re-rank on shortlists.

Encryption at rest/transit, tenant isolation, ACL on metadata filters, PII in embeddings, and audit logging.

efSearch, nprobe, over-fetch for filters, offline benchmarks, and continuous monitoring of retrieval quality.

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

Bootstrap strategies, fallback retrieval, hybrid search defaults, and UX for new tenants or collections.

PCA, Matryoshka embeddings, learned compression, and recall impact when shrinking vector size.

ANN parameter tuning, rebuild windows, incremental indexing, and serving fresh vectors without missing SLOs.

Embedding geometry and index metric choice — normalization, MIPS, and provider defaults for text retrieval.

Core ANN index families — graph-based HNSW, inverted-file IVF, and locality-sensitive hashing LSH — with recall, build cost, and memory trade-offs.

Hard vector DB question on tenant isolation, noisy neighbors, and ACL safety.

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.

Latency, availability, freshness, recall, and error budget definitions with realistic dependencies.

Company-based system design: sharded ANN, metadata pre-filtering, query routing, reranking, and latency SLOs at marketplace scale.

Write buffering, mutable segments, async merge, backpressure, and consistency windows for hot ingestion paths.

Learned sparse representations, inverted index integration, lexical expansion, and fusion with dense ANN.

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