Intermediate interview questions in AI & ML, page 4
Implement OAuth 2.0 flow to get an access token for API requests
Tests your grasp of OAuth 2.0 grant-type selection and token lifecycle. Strong answers match the script context to client credentials or authorization code flow, detail the token endpoint exchange, and address refresh and expiry.
How do you build dev and production Docker images from one source?
Mastery of Docker multi-stage builds for isolating dev and production dependencies. Use a base stage, a dev target with linters and tests, and a lean production target copying only the build artifact.
Regularization techniques for an overfitting CNN
Data augmentation expands the effective dataset, dropout prevents co-adaptation, weight decay penalizes large weights, plus early stopping and batchnorm.
How do you version and distribute Docker dev environments consistently?
Tests immutable dev environment distribution. Strong answers cover: versioned Dockerfiles in Git, immutable image tags pushed to a registry, and enforcing identical pulls for CI and developers. Red flag: using the "latest" tag or local Dockerfile rebuilds.
Why does your RAG ignore or contradict retrieved context?
Tests separation of retrieval failures from generation grounding in RAG. Strong answers trace symptoms to root causes like bad chunks, prompt ordering, or parametric knowledge override, then outline systematic debugging. Do not just say hallucination.
Evaluating a RAG system end to end
Measure retrieval with context recall or precision, and generation with faithfulness and answer relevance, attributing failures to the right stage.
ResNet residual blocks and the degradation problem
A residual block learns F(x) and adds the identity input x, so layers fit a residual; this eases gradient flow and solves the degradation problem.
Receptive fields in convolutional networks
Receptive field is the input region affecting a neuron; it grows with depth, larger kernels, and stride. It matters for capturing context in detection and segmentation.
How would you modify retrieval architecture for hybrid text and SQL RAG?
It tests unified retrieval across unstructured text and structured SQL. Outline a query planner that routes to vector search or text-to-SQL, joins the results, and synthesizes a final answer. Never suggest embedding the whole database as text chunks.
Uses of the 1x1 convolution
A 1x1 conv is a per-pixel linear combination across channels; it reshapes channel depth cheaply and adds nonlinearity. Uses: dimensionality reduction in bottlenecks and channel mixing.
What is data leakage in preprocessing and cross-validation?
This tests recognition of data leakage through preprocessing statistics. A strong answer defines leakage, describes scaling using global statistics before CV splits, and states transformers must be fit per training fold.
Diagnosing poor distributed training scaling
Communication overhead (gradient all-reduce, interconnect), data-loading starvation, load imbalance, and small per-GPU batches; profile with the PyTorch profiler and Nsight.
Why is scaling unnecessary for trees but critical for SVM or K-Means?
Tests whether you understand model internals. Trees split on rank order, so scale is irrelevant. SVM and K-Means rely on distance or margin geometry, making magnitude dominate.
Robust checkpointing strategy for multi-day training jobs and seamless resumption
Tests production-grade distributed training reliability. Cover async atomic checkpoints, MTBF-based cadence, tiered storage, and recovery drills. Red flag: blocking synchronous writes that ignore silent corruption or straggler finalization.
Design training job submission to a shared Kubernetes cluster
Gateway with artifact caching; namespace quotas; GPU schedulers like Volcano; Prometheus metrics and cost attribution.
Describe a ReAct agent architecture for multi-step dependent tool calls
Sketch ReAct's thought-action-observation cycle; keep state in an append-only trajectory; re-plan after each observation.
Compare Airflow and Kubeflow for ML training pipelines
Tests orchestrator-to-workload fit. Strong answers contrast Airflow's data integration and Python DAGs with Kubeflow's K8s scaling, container reproducibility, and experiment tracking. Red flag: claiming one is always better without stage-specific reasoning.
What fixes an LLM agent's incorrect JSON arguments for a complex tool?
Tests mixing prompting with system guardrails for valid tool JSON. Outline: few-shot demos plus CoT prompting; schema validation, constrained decoding, and retries. Red flag: weak prompts without validation or structured output.
What is data pipeline idempotency and how do you design for it?
This tests resilient pipeline design under failure. A strong answer defines idempotency as identical output on repeated runs, highlights safe retries and partial failure recovery, and proposes idempotency keys with atomic writes for daily API loads.
How would you partition a massive user events table?
Tests whether you map query patterns to storage layout to cut bytes scanned. Strong answers pick time-based partitioning for range pruning, cluster by high-cardinality filters, and justify against WHERE clauses.
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