Interview questions in AI & ML, page 22
What is shadow deployment for ML models?
New model receives mirrored live traffic but its predictions are logged, not served; validates real-world behavior and latency without user risk.
Preprocessing conversations to protect privacy before fine-tuning
Detect and redact PII with NER plus regex, choose redaction versus pseudonymization, and validate recall.
Why version data and model artifacts, not just code
Code alone cannot reproduce a model; data and artifact versioning enable rollback, debugging, audit.
How is an HDR radiance map constructed from exposures?
Recover the inverse camera response function from corresponding pixels, linearize each exposure to radiance, then merge with confidence weights into a floating-point radiance map.
Measuring fairness in an embedding-based text classifier
Define group definitions, apply demographic parity and equalized odds, and address noisy labels and implicit group membership.
Zero-downtime model updates with blue-green or canary
Blue-green swaps full traffic after validation, canary ramps a small slice; both need health, latency, and quality monitoring plus instant rollback.
Feature detector vs feature descriptor.
A detector finds where interesting points are, a descriptor encodes the local appearance around each so points can be matched.
Compare Canary and Blue/Green ML deployments and model-specific metrics
Contrast Canary gradual shift vs Blue/Green instant swap; highlight silent failures, data drift, prediction distribution; cite accuracy and calibration.
Practical explainability for an LLM loan summary
Use attribution-by-design with grounded citations, structured rationales, and a deterministic rules layer instead of slow per-token SHAP.
Minimizing model prediction latency end to end
Shrink the model via quantization, pruning, distillation, compilation; cut infra latency via caching, edge, faster runtimes.
Why learn detection and description jointly like SuperPoint?
A shared backbone jointly optimizes detection and description for matching, sharing computation and learning data-driven robustness instead of hand-crafted heuristics.
Design a multi-tenant GPU serving system for hundreds of fine-tuned models
Tests GPU memory tradeoffs versus cold-start latency in multi-tenant serving. Strong answers propose tiered CPU staging, predictive pre-warming, and disaggregated prefill and decode. Red flag: keeping all models GPU-resident or ignoring transfer overhead.
What is a model registry and how does it enable CD?
A registry versions models with metadata, lineage, and stage tags; CD watches stage transitions to trigger deploys.
Data lineage and machine unlearning for a fine-tuned LLM
Version and fingerprint datasets, record transforms and which checkpoint saw what, and enable unlearning via retraining, data sharding, or approximate gradient methods.
Programmatically detect and redact PII in text
Regex for structured PII plus NER for names and places, redact or tokenize, then validate recall.
What is Bundle Adjustment and why is it tractable?
Jointly refine 3D points and camera poses by minimizing reprojection error, expensive due to many coupled parameters; sparsity of the Jacobian and the Schur complement make it tractable.
Designing an autonomous research-and-report agent
Planner that decomposes goals, short-term scratchpad plus long-term vector memory, structured tool calls, and a reflect-retry loop for error correction.
Quantifying performance disparity across subgroups
Compute per-group precision, recall, FPR, FNR, compare via fairness metrics; visualize with grouped bars or per-group confusion matrices.
Improving small object detection
Raise input resolution and tile, use feature pyramids for high-res features, tune anchors and copy-paste augmentation.
Explain dynamic batching in inference servers and its trade-off
Dynamic batching launches when a time window or max size is met, improving throughput over static batching, but short ones wait for the slowest.
We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.
See open roles