Learn the work behind Data, AI & Forward Deployed Engineering
Practical explanations, career decisions and reproducible workflows. Read the reasoning, inspect the evidence and follow the next skill into a real programme.
Metadata filters: enforce eligibility before similarity ranking
Similarity answers “which text looks related?” It does not answer “may this user receive it?” or “which version is active?” Eligibility must constrain the candidate set before ranking and before content reaches a model o
Missing data mechanisms with an analyst's decision checklist
Investigate why values are missing before choosing deletion or imputation. MCAR, MAR and MNAR describe assumptions about the missingness process relative to observed and unobserved data; they are not labels a null-count
Missing-value indicators: when missingness carries information
Imputation fills a value so a model can compute. A missingness indicator preserves the fact that a value was absent. That fact can be predictive when collection, eligibility or behaviour affects whether the field is obse
Mock an external API without testing your own mock
A fake that always returns whatever the application expects can make broken integration code look correct. Test both sides of the adapter contract.
Model retraining triggers based on evidence
Retraining is an experiment, not a repair command. New data can be mislabeled, shifted or incompatible. A good policy distinguishes investigation, candidate training and production promotion.
Monitor a no-code automation for silent failures
A workflow can show no error while an event never arrived, a filter discarded it or an incomplete run went unnoticed. Reconcile business counts rather than relying only on technical failure notifications.
Monitor calibration after a business-policy change
A business policy can change who receives an action, which outcomes are observed and the relationship between scores and labels. A calibration map fitted before the change may no longer represent the post-policy populati
Monitor model input drift without treating every alert as failure
Input drift means the serving feature distribution differs from a reference. Performance can remain stable under some shifts and fail without a large marginal shift. Treat drift as an investigation signal, then confirm i
Monotonic constraints: encode a justified business relationship
A monotonic constraint tells a model that its prediction may only move in one direction as a feature increases while other model inputs are held fixed. This can stabilize behaviour where the relationship is known and def
Multi-output regression with shared and separate models
Multi-output regression predicts several numeric targets for each row. A shared model can exploit common structure and produce predictions together. Separate models can give each target its own representation and tuning.
Multi-query retrieval with bounded cost
Different phrasings can surface evidence missed by one query, but unlimited variants multiply model calls, searches and duplicate context. Set a maximum and measure incremental value.
Multimodal RAG: connect an image claim to its source
A citation to a long PDF does not establish which diagram, label or region supports an image-derived claim. Multimodal RAG needs evidence coordinates that a reviewer can inspect.
Not sure which programme fits?
Tell us your background and we will map it to the right entry point — including saying so when a cheaper programme is the better fit. A counsellor replies within one working day.