CrackML by @ml.with.umang
Interview questions / ML Fundamentals
ML Fundamentals interview question

Describe the Segment Anything Model (SAM) and how it works

Describe the Segment Anything Model (SAM) and how it works.

mediumconceptEvidence 75/1001 source reportAmazon

The 60-second answer

Explain token embeddings plus positional information feeding repeated attention and feed-forward blocks. Self-attention forms Q, K, and V, computes scaled similarities, then mixes value vectors.

Build the answer in this order

1
Give the core idea

Explain token embeddings plus positional information feeding repeated attention and feed-forward blocks.

2
Explain how it works

Self-attention forms Q, K, and V, computes scaled similarities, then mixes value vectors.

3
Compare alternatives

Multi-head attention learns multiple interaction subspaces while residuals and normalization stabilize training.

4
State failure modes + validation

Call out quadratic attention cost with sequence length and masking requirements.

A useful interview mental model

This is the shape of a strong answer—not a script to memorize.

01Definition
02Mechanism
03Trade-offs
04Failure modes
05When to use

Senior-level signal

  • Discuss KV caching and efficient attention kernels for serving.
  • Compare encoder-only, decoder-only, and encoder-decoder objectives based on the task.

What the interviewer is really testing

Mechanistic understanding, assumptions, trade-offs, and whether you can turn a definition into a model decision.

Likely follow-up questions

What assumption makes this approach work?
When would you choose the strongest alternative instead?
What production or data failure mode changes your answer?

Common weak-answer patterns

  • Reciting a definition without mechanism or assumptions.
  • Claiming one technique is always better without a data regime.
  • Stopping before failure modes, validation, or deployment implications.