What you should be able to do
Implement lexical search
Evaluate retrieval quality
Build intent routing
Design knowledge-grounded assistants
Every module is now a full lesson.
Tokenization
Convert raw text into stable units for retrieval or models.
TF-IDF
Create sparse text vectors that emphasize terms important in one document but rare globally.
BM25
Rank documents lexically with term saturation and document-length normalization.
Embeddings
Represent items as dense vectors so semantic similarity can be measured.
Reranking
Build a working mental model of Reranking then connect it to implementation evaluation and production trade-offs.
Intent classification
Build a working mental model of Intent classification then connect it to implementation evaluation and production trade-offs.
RAG architecture
Build a working mental model of RAG architecture then connect it to implementation evaluation and production trade-offs.
Projects that prove the skill
Cortex retrieval engine
Use a baseline first then instrument the result and document failure cases.
design with cortex →Knowledge search
Use a baseline first then instrument the result and document failure cases.
design with cortex →Article copilot
Use a baseline first then instrument the result and document failure cases.
design with cortex →How progress is judged
nDCG
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
MRR
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
Calibration
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
Grounding quality
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
Turn the track into a personal plan.
Cortex can break this path into daily sessions and adjust based on completed lessons, interview results and your saved learning goals.
Ask Cortex to plan it →