MST 506Mastery · 90 days3 US credit hours·Mastery course · Upper-division / professional elective·v1 · updated 3 Oct 2026

AI Data Engineering Mastery

University / Board Instructor Student Outcomes & Skills

Course outcomes

CO1

Demonstrate Foundations — Data, Retrieval Theory & the Corpus competence: complete the Day 1–15 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C2 Understand

Hybrid search, chunking & reranking Document parsing & layout-aware extraction (Docling, tables, OCR)Chunking strategy design & measurement (semantic, late, contextual)Embeddings & vector search Postgres data modelling, indexing & query tuning Evaluation engineering with golden sets Orchestration & pipeline engineering (Airflow, Dagster, dbt, dlt)

CO2

Demonstrate Vector Databases & Retrieval Engineering competence: complete the Day 16–30 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C3 Apply

Hybrid search, chunking & reranking Embeddings & vector search Postgres data modelling, indexing & query tuning Query understanding: rewriting, decomposition, adaptive retrieval Metadata design, tenant isolation and clearance-aware filtering LLM cost & latency estimation Team delivery & technical communication

CO3

Demonstrate Knowledge Graphs, Ontologies & GraphRAG competence: complete the Day 31–45 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C4 Analyse

Knowledge-graph traversal (Neo4j)Ontologies & semantic standards (RDF, OWL, SKOS, SPARQL, SHACL)Entity & relation extraction from text with LLMs Entity resolution & record linkage (Splink, blocking, Fellegi–Sunter)Team delivery & technical communication

CO4

Demonstrate Evaluation, Observability & Retrieval Quality competence: complete the Day 46–60 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C4 Analyse

Hybrid search, chunking & reranking Chunking strategy design & measurement (semantic, late, contextual)Entity & relation extraction from text with LLMs Entity resolution & record linkage (Splink, blocking, Fellegi–Sunter)Evaluation engineering with golden sets CI regression gates for AI LLM-as-judge calibration Failure taxonomy, improvement flywheel, labelling operations and incident response LLMOps observability & SLOs Streaming ingestion & CDC (Kafka, Debezium, freshness SLAs)LLM cost & latency estimation

CO5

Demonstrate Production Platform, Security & Governance competence: complete the Day 61–75 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C5 Evaluate

Orchestration & pipeline engineering (Airflow, Dagster, dbt, dlt)Lakehouse storage, table formats & reproducibility (Iceberg, DuckDB)Streaming ingestion & CDC (Kafka, Debezium, freshness SLAs)Index lifecycle: zero-downtime rebuild, blue/green, rollback AI security & prompt-injection defence Metadata design, tenant isolation and clearance-aware filtering Responsible AI & regulatory compliance Structured retrieval: text-to-SQL & semantic layers

CO6

Demonstrate Agentic Retrieval, Scale & Mastery competence: complete the Day 76–90 builds, explain the underlying theory, and defend the phase artefact under live questioning.

C6 Create

Document parsing & layout-aware extraction (Docling, tables, OCR)Embeddings & vector search Query understanding: rewriting, decomposition, adaptive retrieval Agentic & self-correcting retrieval (routing, Self-RAG, CRAG, multi-hop)Structured retrieval: text-to-SQL & semantic layers LLM cost & latency estimation Team delivery & technical communication

Phases & skills

Phase	Topic	Outcomes	Deliverable	Skills
1	Foundations — Data, Retrieval Theory & the Corpus Days 1–15 · C2	CO1	CAPSTONE (Phase 1) — A measured, reproducible corpus	Hybrid search, chunking & reranking Document parsing & layout-aware extraction (Docling, tables, OCR)Chunking strategy design & measurement (semantic, late, contextual)Embeddings & vector search Postgres data modelling, indexing & query tuning Evaluation engineering with golden sets Orchestration & pipeline engineering (Airflow, Dagster, dbt, dlt)
2	Vector Databases & Retrieval Engineering Days 16–30 · C3	CO2	CAPSTONE (Phase 2) — A benchmarked hybrid retrieval service	Hybrid search, chunking & reranking Embeddings & vector search Postgres data modelling, indexing & query tuning Query understanding: rewriting, decomposition, adaptive retrieval Metadata design, tenant isolation and clearance-aware filtering LLM cost & latency estimation Team delivery & technical communication
3	Knowledge Graphs, Ontologies & GraphRAG Days 31–45 · C4	CO3	CAPSTONE (Phase 3) — A domain knowledge graph with GraphRAG	Knowledge-graph traversal (Neo4j)Ontologies & semantic standards (RDF, OWL, SKOS, SPARQL, SHACL)Entity & relation extraction from text with LLMs Entity resolution & record linkage (Splink, blocking, Fellegi–Sunter)Team delivery & technical communication
4	Evaluation, Observability & Retrieval Quality Days 46–60 · C4	CO4	CAPSTONE (Phase 4) — The evaluation and observability harness	Hybrid search, chunking & reranking Chunking strategy design & measurement (semantic, late, contextual)Entity & relation extraction from text with LLMs Entity resolution & record linkage (Splink, blocking, Fellegi–Sunter)Evaluation engineering with golden sets CI regression gates for AI LLM-as-judge calibration Failure taxonomy, improvement flywheel, labelling operations and incident response LLMOps observability & SLOs Streaming ingestion & CDC (Kafka, Debezium, freshness SLAs)LLM cost & latency estimation
5	Production Platform, Security & Governance Days 61–75 · C5	CO5	CAPSTONE (Phase 5) — The governed production platform	Orchestration & pipeline engineering (Airflow, Dagster, dbt, dlt)Lakehouse storage, table formats & reproducibility (Iceberg, DuckDB)Streaming ingestion & CDC (Kafka, Debezium, freshness SLAs)Index lifecycle: zero-downtime rebuild, blue/green, rollback AI security & prompt-injection defence Metadata design, tenant isolation and clearance-aware filtering Responsible AI & regulatory compliance Structured retrieval: text-to-SQL & semantic layers
6	Agentic Retrieval, Scale & Mastery Days 76–90 · C6	CO6	MASTERY CAPSTONE — The flagship system	Document parsing & layout-aware extraction (Docling, tables, OCR)Embeddings & vector search Query understanding: rewriting, decomposition, adaptive retrieval Agentic & self-correcting retrieval (routing, Self-RAG, CRAG, multi-hop)Structured retrieval: text-to-SQL & semantic layers LLM cost & latency estimation Team delivery & technical communication