Adobe ML & AI interview questions.
Questions in the CrackML corpus associated with Adobe. Use company evidence as a prioritization signal, not a promise that an exact question will repeat.
Design an end-to-end image-and-text pipeline to predict document aspect ratio.ML System Design · hard · Evidence 77/100Design a color suggestion system.ML System Design · hard · Evidence 77/100How would you handle an imbalanced dataset?ML Fundamentals · medium · Evidence 76/100Explain the relationship between self-attention and Transformer representations.GenAI & LLM · medium · Evidence 41/100How would you design image augmentation without corrupting labels?ML Fundamentals · medium · Evidence 41/100How would you model structured and unstructured signals from the same document?ML System Design · hard · Evidence 41/100How would you fuse image and text representations for a document model?GenAI & LLM · hard · Evidence 41/100How would you monitor distribution drift in a multimodal model?ML System Design · hard · Evidence 41/100When would you use a multimodal model instead of separate unimodal models?GenAI & LLM · medium · Evidence 41/100How would you evaluate a computer-vision model beyond aggregate accuracy?ML Fundamentals · medium · Evidence 41/100How would you evaluate the relevance of a color-suggestion model?ML Fundamentals · medium · Evidence 41/100How would you diagnose domain shift in image data?ML Fundamentals · hard · Evidence 41/100How would you construct labels for a multimodal document prediction task?ML System Design · medium · Evidence 41/100When would you choose a CNN over a Vision Transformer?ML Fundamentals · medium · Evidence 41/100How would you handle a missing image or missing text modality at inference time?ML System Design · hard · Evidence 41/100