sampling

Every LLM product tunes these knobs, and the interviewer wants to hear what each one does to the probability distribution and which setting suits which task. That includes why factual and creative tasks call for opposite settings.

How you decode from the model's probabilities shapes the output as much as the model itself. The signal is knowing the deterministic vs sampling methods and where each fits (factual vs creative). Here is the answer.

Neural text degeneration is a known failure of likelihood-maximizing decoding, not a broken model. The fixes are specific decode-time knobs. Here is which lever to reach for and what each one costs.

Most people know MCP exposes tools. The deeper signal is the complete primitive set (resources, prompts, sampling, roots) and the patterns: server composition, sampling for nested LLM calls, and scoping access safely.

Drawing a uniform sample from a stream too large for memory (or whose length stays unknown) is a genuine data-engineering problem. What interviewers watch for: the replace-with-decreasing-probability trick and a telescoping proof. Here is the answer.

Every chat model's 'temperature' and 'top_p' knobs come down to a few lines of logit surgery. Implementing them proves you understand decoding rather than just calling it. Here is the from-scratch version.

Negative sampling in word2vec and recommendation pulls millions of weighted samples; running each at O(log n) becomes a bottleneck. The alias method turns each draw into O(1) after an O(n) setup. Here it is.

When labels exist only for the cases you already acted on, the model learns a distorted world: strong offline, blind to everyone you never saw. Worse, its own decisions choose the next labels. Here is how to spot it and counter it.

Bayesian inference requires an intractable normalizing constant, and MCMC works around it. The signal is explaining the acceptance ratio, detailed balance, and why you can drop the constant entirely. Here is the answer.

Building a training set from a billion-row table means sampling, and the naive 'ORDER BY random() LIMIT n' sorts the whole table. Stratified sampling takes even more care. Here are both, done efficiently.

Sampling cost factors cleanly into steps, forward passes per step, and cost per step, and each factor has a different lever. Two of the biggest wins are free, and most teams take neither.