MLE · system designersData pipeline · training · evaluation

ML Systems · Machine Learning Engineer

The full applied pipeline: splitting and scaling data, cross-validation, optimizer updates, and the calibration and importance checks before shipping.

3 phases · 26 problems · 26 unique

Start timed mock5 problems · 4 min each

Your progress

0/26 · 0%

Continue track · Deterministic Train/Test Split

1Warm-up

0/8

Deterministic Train/Test Split
ml-021ML Fundamentals
Easy
Standardization of Feature Values
ml-023ML Fundamentals
Easy
Min-Max Scaling
ml-024ML Fundamentals
Easy
Dense Layer Forward
dl-010Deep Learning
Easy
Gradient Descent Step
ml-083ML Fundamentals
Medium
Train/Validation/Test Sizes
ml-128ML Fundamentals
Easy
Gradient Descent
op-001Optimization
Medium
Exponential LR Schedule
op-005Optimization
Easy

2Core

0/10

K-Fold Split Indices
ml-010ML Fundamentals
Medium
Shuffled Train/Test Split
ml-022ML Fundamentals
Medium
Stratified Train/Test Split
ml-049ML Fundamentals
Medium
Cross-Validation Mean Score
ml-118ML Fundamentals
Medium
Grid Search Best Params
ml-122ML Fundamentals
Medium
Random Search Picks
ml-123ML Fundamentals
Medium
MLP Forward Pass
dl-004Deep Learning
Medium
Momentum Update Step
ml-131ML Fundamentals
Medium
Momentum Optimizer
op-003Optimization
Medium
AdamW Decoupled Weight Decay
op-011Optimization
Medium

3Hard

0/8

Expected Calibration Error by Probability Bins
ml-101ML Fundamentals
Hard
Adam Optimizer Step
ml-132ML Fundamentals
Hard
Bootstrap Standard Error
ml-135ML Fundamentals
Hard
Permutation Importance MSE
ml-141ML Fundamentals
Hard
Transformer Encoder Block Parameter Count
dl-091Deep Learning
Hard
Matrix Factorization SGD Step
ml-220ML Fundamentals
Hard
Mini-Batch SGD for Linear Regression
op-002Optimization
Hard
Adam Optimizer
op-004Optimization
Hard