Airbnb AI & ML Engineer interview questions

Every team ships English first, then finds that the retriever, the prompt, the latency budget and the cost model each degrade differently in the next five languages. The applied playbook looks nothing like the model-level answer, and the thing that sinks launches is the eval set nobody built.

The words encode a partial order between characters. Turn each adjacent pair into a directed edge, then topologically sort. The traps are the prefix edge case and detecting contradictions. Here is the full solution with cycle handling.

Binary search on the answer solves minimize-the-maximum and capacity problems by guessing the result and checking feasibility in a monotone predicate. The signal is spotting monotonicity and writing a clean feasibility function. Here is the answer.

For search and recommendation, A/B tests can be slow and noisy because they compare different users. Interleaving compares two rankers within the same user's results and detects winners with far less traffic. Here is how.

Standard A/B math assumes one user's treatment doesn't affect another's outcome. In marketplaces and social networks that assumption breaks and your estimate is biased. The signal is naming SUTVA and the right randomization unit. Here is the answer.

Prophet treats forecasting as curve-fitting trend plus seasonality plus holidays, not as a stochastic process. The signal is knowing why that design wins on business data and where it quietly fails. Here is the answer.

Funnels look like simple counts until you require the steps happen in order and within a window. Counting each step independently overstates conversion. Here is the ordered-funnel query.

Days with zero events simply don't appear in an event table, so a 7-day average silently averages the wrong 7 rows. A date spine makes the missing days explicit. Here is the pattern.

A rider taps request and within seconds a nearby driver is assigned. The interesting problems are geospatial indexing of moving drivers, the matching objective (nearest is not always best), and handling the race where two riders want the same car. Here is how to build it.

In payments, a duplicate charge or a lost credit is not a bug, it is a financial incident. The design hinges on idempotency keys, double-entry bookkeeping, and an append-only ledger that can be audited and reconciled. Here is how money systems stay correct.

Find the 20 nearest restaurants within 5km, fast, for millions of users. A naive distance scan over every place is hopeless. The design is about spatial indexing, geohash or quadtree partitioning, and handling dense cities versus empty regions. Here is how proximity search works.

Background jobs fail, retry, and get redelivered. If a job sends an email or charges a card, running it twice is a real problem. The design is at-least-once delivery plus idempotent handlers, visibility timeouts, and dead-letter queues. Here is how to make jobs safe.

A data engineer renames a column and three production models silently start scoring on garbage. Features are a shared contract, and changing them needs the same care as a breaking API change. Here is the discipline.

Anyone can wire tasks into a DAG. The signal is the patterns that keep it correct under retries and backfills: idempotency, data-aware triggering, and the asset model. Here is what separates a flaky pipeline from a trustworthy one.

A favorite practical screen at the labs, because it tests concurrency, time handling, and judgment in 20 lines. The trap is the background thread that wastes CPU. Here is the lazy-refill version interviewers want, plus the follow-ups.

Applied AI rarely waits for certainty, and companies (Amazon's Bias for Action, NVIDIA's speed) test whether you can act decisively without freezing or being reckless. The signal is a reversible, well-reasoned call with a plan to validate. Here is the arc that lands.

A classic that tests whether you reach past sorting for the right structure. The signal is the heap solution (O(n log k)), the bucket-sort O(n) trick, and how it changes for an unbounded stream. Here is the answer.

A sudden 22-point AUC jump is a gift and a warning. Junior candidates celebrate; strong ones get suspicious and know exactly which leakage checks to run before anything ships.

Autocomplete is the canonical trie question, and it tests whether you reach for the right structure instead of scanning a word list. The signal is O(prefix) lookup, the DFS to collect completions, and the follow-ups (ranking, memory). Here is the build.

A common ML-coding check that verifies you actually understand the metrics you quote. The signal is getting TP/FP/FN/TN right and knowing macro vs micro averaging for multiclass, not reaching for sklearn.

Imbalance shows up in fraud, churn, and abuse, and the naive answer (oversample, done) leaks data and inflates offline metrics. The signal is preferring cost-sensitive learning, fixing the metric, and resampling correctly. Here is the full toolkit with tradeoffs.

This is two questions hiding as one: how would you have caught it before full rollout, and how do you debug it now. Answer both and you signal senior judgment. Here is the staged-rollout and root-cause playbook.