Courses / Live bootcamps
RAG and Search Engineering Bootcamp
Retrieval that actually finds the right thing, measured, at scale.
- weeks, live on Zoom
- 12
- hours a week
- 15
- deployed projects
- 6
- minutes 1-1, every week
- 30
Who it is for, and what you receive.
Engineers building search or question-answering over documents, and anyone whose RAG demo fell apart in production.
Before you start
Python and SQL; some exposure to an LLM API.
Skills
- Python
- search
- embeddings
- vector databases
- reranking
- RAG
- evals
A week, about 15 hours
- Live on Zoom
- 4h
- Recorded lessons and exercises
- 6h
- The project
- 5h
- 1
Six deployed projects
Each graded by Nova against a published rubric and signed off by the instructor at the gate.
- 2
The recorded lessons
The track's lessons and exercises, graded line by line, open for twelve months after the cohort ends.
- 3
Live on Zoom every week
A 90-minute live code review, a 60-minute squad lab, 60 minutes of office hours, and a 30-minute 1-1 with your instructor.
- 4
Your hiring plan
Opened in week 1 and reviewed in every 1-1: target roles, the gap map, the proof list, weekly actions, an interview log, the outcome.
- 5
The record
Every grade and every project with its repository at square1ai.com/u/{handle}, and the recording of your viva, verifiable by any employer.
- 6
The certificate
A credential ID that resolves at square1ai.com/verify to the real completion.
- 7
The hiring sprint
Weeks 11 and 12: CV and portfolio from graded work, applications, mock interviews scored against the role, demo day.
- 8
Nova for twelve weeks
A tutor with every submission of yours in its memory, at 2am as well as in class.
Twelve weeks in six blocks.
Each block teaches for a week, then you build and deploy a project, then a gate checks it before the next block opens. The project and its gate are the block's record entry.
Live time each week on Zoom: a 90-minute class where the instructor reviews real submissions, a 60-minute squad lab, 60 minutes of office hours, and your own 30-minute 1-1. Nothing is lectured live; the recorded lessons do that.
- 1
Search fundamentals
Weeks 1 to 2Week 1
Search fundamentals
- BM25 and lexical ranking
- Embeddings and vector indexes
- Hybrid retrieval
- Query understanding
You build: A hybrid search service
Week 2
Project 1: hybrid search
- Labelled query sets
- Recall at k
You build: Hybrid search over a real corpus with recall measured
Project 1, the gate at week 2
Hybrid search
Search a 50,000-document public corpus better than either lexical or vector alone.
You hand in
- Search service
- Labelled query set
- Recall report
The gate
Recall at ten measured against the labelled set.
- 2
Chunking and ingestion
Weeks 3 to 4Week 3
Chunking and ingestion
- Parsing PDFs, tables and code
- Chunking strategies
- Metadata
- Incremental ingestion
You build: Ingestion pipeline
Week 4
Project 2: freshness
- Change detection
- Scheduled reindexing
You build: A pipeline that keeps the index fresh
Project 2, the gate at week 4
Ingestion
Keep the index fresh as documents change.
You hand in
- Parsers for PDF, tables and code
- Chunking
- Incremental pipeline
The gate
Updated documents searchable within the pipeline's interval.
- 3
Reranking and generation
Weeks 5 to 6Week 5
Reranking and generation
- Cross-encoders
- Grounded generation
- Citations
- Faithfulness
You build: A cited answer engine; squads form
Week 6
Project 3: cited answers
- Citation interfaces
- Faithfulness evals
You build: RAG application with checkable citations
Project 3, the gate at week 6
Cited answers
Answer questions with citations a reader can check.
You hand in
- Reranker
- Answer engine
- Citation interface
- Faithfulness eval
The gate
Faithfulness and citation accuracy measured.
- 4
Evaluation
Weeks 7 to 8Week 7
Evaluation
- Retrieval evals
- End-to-end evals
- Query analysis
- Failure taxonomy
You build: Eval suite
Week 8
Project 4: the failure report
- Classifying failures
- Prioritising fixes
You build: Eval suite and failure report, published
Project 4, the gate at week 8
Evaluation
Find out why it fails.
You hand in
- Retrieval and end-to-end evals
- Failure taxonomy with counts
The gate
The top three failure classes named with counts.
- 5
Scale
Weeks 9 to 10Week 9
Scale
- Indexes at millions of documents
- Latency, cost and caching
- Multi-tenancy
- SLOs
You build: Architecture design
Week 10
Project 5 and the viva
- Multi-tenant retrieval
- Defending cost at scale
You build: Multi-tenant retrieval with SLOs; the viva
Project 5, the gate at week 10
Scale
Serve many tenants at millions of documents inside an SLO.
You hand in
- Multi-tenant architecture
- Caching
- Cost model
- SLO dashboard
The gate
The viva: defend the architecture and its cost at scale.
- 6
Employer brief and hiring sprint
Weeks 11 to 12Week 11
Employer brief
- A real problem from a hiring partner, in squads
- A partner's search problem
- Working to someone else's definition of done
You build: The employer brief in progress
Week 12
Hiring sprint
- CV and portfolio built from graded work
- Applications and follow-ups in the hiring plan
- Mock interviews scored against the role
- Demo day
You build: Project 6 delivered; demo day
Project 6, the gate at week 12
Employer brief
A partner's search problem.
You hand in
- The brief delivered
- Demo day
The gate
The brief's owner accepts the result.
What you can do by week 12.
Six retrieval systems and a retrieval eval method you can apply anywhere, from a hybrid index to a multi-tenant platform with SLOs.
- 1
Build lexical, vector and hybrid retrieval and measure recall against a labelled query set.
- 2
Parse and chunk PDFs, tables and code, and keep an index fresh with incremental ingestion.
- 3
Rerank and generate grounded answers with citations, and measure faithfulness.
- 4
Evaluate retrieval end to end and classify its failures.
- 5
Run retrieval at millions of documents with latency, cost and multi-tenant isolation.
- 6
Defend a retrieval architecture and its cost.
Roles this prepares you for
- Search engineer
- RAG engineer
- AI engineer
- ML engineer (retrieval)
No placement rate is shown, because there are no graduates to count yet. The roles above are what the projects are built for.
Your record at week 12.
Every exercise and project is graded by Nova against a rubric you can read, and every grade is kept on one page an employer can open and run. This is what the programme writes to it.
- Graded, line by line
- Nova reads every submission against the brief and the rubric and returns a score, what you did well and what to fix.
- Six gates
- A block does not open until the previous project passes its gate. You always know where you are and what is next.
- A weekly 1-1
- Thirty minutes with your instructor, who has already read your code before the call.
- One page an employer can run
- Every grade, project and the viva recording at /verify. An employer opens it, runs the code and watches you defend it.
Record, RAG and Search Engineering Bootcamp
Example
- Week 2Graded, gate signed
Hybrid search
Recall at ten measured against a labelled query set
- Week 4Graded, gate signed
Ingestion
Updated documents are searchable within the pipeline's interval
- Week 6Graded, gate signed
Cited answers
Faithfulness and citation accuracy measured
- Week 8Graded, gate signed
Evaluation
The top three failure classes are named with counts
- Week 10Graded, gate signed
Scale
A viva: defend the architecture and its cost at scale
- Week 12Graded, gate signed
Employer brief
The brief's owner accepts the result
- Weeks 1 to 12Kept
Twelve 1-1 notes
What your instructor saw in your work each week, and what you agreed to do next.
- Week 12Kept
Your hiring plan and its outcome
Target roles, the gap map, applications, interviews and where you landed.
The entries, not the grades: those are yours to earn. The page lives at /verify and an employer needs no account to open it.
8 entries, twelve weeks. One email when applications open.
How we help you find a job.
The last block is not curriculum. It is the hiring sprint, and the proof you built in the ten weeks before it.
- 1
Your hiring plan, from week 1
Six parts you and your instructor keep: target roles, the gap map from real postings, the proof to send, weekly actions, an interview log, the outcome. Read before every 1-1.
- 2
The hiring sprint
Weeks 11 and 12: CV, portfolio, applications, mock interviews, and demo day in front of hiring partners.
- 3
A record an employer can run
Your six deployed projects and the recorded viva on /verify. An employer opens it, runs the code and watches you defend it.
- 4
The career agent
Paste a real job posting at /career and it maps the role to your graded work and what to do next.
- 5
The roles directory
Every role we prepare people for, what it pays and what it asks, at /roles.
One email when applications open.
Fifty seats, one instructor, twelve weeks. The waitlist hears the date and the price first, and nothing is charged before the cohort exists.