InterviewsVector
Capability spine

Arc 07 · Senior AI Engineer

Retrieval and Knowledge Systems

Build retrieval as a measurable information system: representations, indexing, chunking, filtering, ranking, grounding, and freshness.

Exit capability: Diagnose a RAG system by stage and improve the right component.

Mapped lessons
7
Published now
1
Full-arc estimate
≈17 hours
Last edited
2026-08-11

Lesson sequence

Live units open into complete labs. Planned units stay visible to show the dependency path, but intentionally have no detail route.

  1. 01

    The Embedding Contract

    Planned

    Version task, model, preprocessing, distance, and dimensionality as one inseparable interface.

    Systems labIntermediate90 min estimate

  2. 02

    Approximate Nearest Neighbors Under a Latency Budget

    Planned

    Compare graph and partitioned indexes through recall, build cost, memory, filtering, and updates.

    Build labAdvanced115 min estimate

  3. 03

    Chunking Is a Recall Policy

    Planned

    Connect document structure and answer span length to retrieval candidates and context waste.

    Failure labIntermediate95 min estimate

  4. 04

    Hybrid Retrieval and Score Fusion

    Planned

    Combine lexical and semantic evidence without comparing incompatible raw scores.

    Build labAdvanced110 min estimate

  5. 05

    Reranking and Context Assembly

    Planned

    Separate candidate generation, expensive relevance judgment, diversity, and final context packing.

    Systems labAdvanced110 min estimate

  6. 06

    Diagnose RAG by Stage

    Live

    Measure corpus, retrieval, reranking, context, generation, citation, latency, and cost separately so failures remain attributable.

    Failure labAdvanced125 min estimateArtifact: Stage-isolated RAG evaluation harness

  7. 07

    Retrieval Security, Deletion, and Freshness

    Planned

    Preserve tenant ACLs, deletion semantics, provenance, and index freshness through ingestion and ranking.

    Design reviewAdvanced105 min estimate