ML — Interview questions

• A/B Testing & Experimentation

  Experiment design, peeking, multiple comparisons, novelty and network effects, switchback, CUPED, the offline–online gap, the OEC and A/A tests.

  11 questions

• AI Agents & LLM Evaluation

  LLM-as-judge and evaluation, guardrails, prompt injection, tool calling, the ReAct loop, hallucination and structured output.

  11 questions

• Gradient Boosting in Practice

  Implementation specifics of XGBoost, LightGBM and CatBoost: tree-growth strategies, histogram splits, GOSS/EFB, ordered target statistics, monotone constraints and hyperparameters.

  11 questions

• Computer Vision

  Convolutional and pooling layers, classic CNN architectures (Inception, ResNet residual blocks), and test-time augmentation.

  20 questions

• Decision Trees

  Single-tree mechanics: split criteria, impurity, pruning, extrapolation limits, feature-importance bias, and native missing-value handling.

  9 questions

• Deep Learning Training

  Neural-network regularization, dropout at train vs inference, normalization layers (BatchNorm/LayerNorm), gradient accumulation, and set/graph architectures.

  21 questions

• Ensembles

  Bagging and Random Forest, gradient boosting and GBDT implementations, the bias/variance effect, hyperparameter tuning, and stacking.

  18 questions

• Feature Engineering

  Encoding, scaling, imputation, outliers, transforms, feature selection, multicollinearity and leak-free temporal features.

  12 questions

• Generalization & Validation

  Bias–variance, the curse of dimensionality, double descent, train/validation/test discipline, cross-validation schemes and the four faces of data leakage.

  11 questions

• Imbalanced Data

  Strategies for class imbalance: resampling, SMOTE, class weights, threshold selection, the anomaly-vs-classification framing and calibration after resampling.

  8 questions

• LLM Architecture

  Transformer internals for large language models: autoregressive generation, the KV cache, MQA/GQA, RoPE, Mixture-of-Experts, tokenizer training and scaling laws.

  10 questions

• LLM Serving & Inference

  Quantization, KV-cache memory, speculative decoding, FlashAttention, continuous batching, decoding strategies, latency vs throughput and serving cost.

  11 questions

• LLM Training & Adaptation

  Fine-tuning vs RAG vs prompting, LoRA/QLoRA, catastrophic forgetting, SFT/RLHF/DPO alignment, instruction tuning and prompting strategies.

  11 questions

• Linear Models & Optimization

  Linear regression, regularization (L1/L2/Elastic Net), the closed-form OLS solution and its pitfalls, and gradient-based optimization.

  18 questions

• MLOps & Production ML

  Training-serving skew, data vs concept drift, feature stores, retraining triggers, reproducibility, model registries and production monitoring.

  11 questions

• ML System Design

  End-to-end design of recommender, fraud, search-ranking, CTR, moderation, dedup, churn, chatbot, matcher and ETA systems, from metric to serving cost.

  14 questions

• Quality Metrics

  Precision, recall and accuracy, the precision/recall threshold trade-off, AUC-ROC and its rank-based properties, and regression metrics under outliers.

  17 questions

• NLP & Transformers

  Word and text embeddings, the Transformer encoder/decoder, self-attention and positional encoding, and BERT for embeddings and question answering.

  18 questions

• Probability & Statistics for ML

  Maximum likelihood, Bayes' theorem, correlation vs independence, the CLT, p-values, distributions, confidence intervals and sample-size/power.

  14 questions

• Retrieval-Augmented Generation

  RAG pipeline anatomy, chunking strategies, hybrid search, vector databases and HNSW, grounding/refusal, and separating retrieval from generation quality.

  9 questions

• Recommender Systems

  Collaborative/content/hybrid filtering, matrix factorization, cold start, candidate generation + ranking, two-tower models, NDCG, position bias and feedback loops.

  11 questions

• Time Series Forecasting

  Stationarity and the ADF test, ACF/PACF, rolling-origin backtesting, GBDT vs ARIMA, multi-step forecasting, seasonality and intermittent demand.

  11 questions

• Unsupervised Learning

  k-means and DBSCAN clustering, PCA and LDA, t-SNE/UMAP, and autoencoder-based anomaly detection.

  12 questions