Perplexity Applied AI Engineer interview questions

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 pull and what each one costs.

The per-token sticker price hides the real decision. Self-hosting only wins past a volume break-even most teams misjudge. Here is the back-of-envelope a staff engineer does on the whiteboard.

Top-k by pure similarity often hands the model five paraphrases of the same paragraph, starving it of the other facts the question needs. The fix is ranking for relevance and novelty at once. Here is how.

Real users type 'what about the new policy?' with no context. Retrieving on those four words returns noise. Here is how strong systems disambiguate before they ever hit the retriever.

More chunks means higher recall but more noise, more cost, and more lost-in-the-middle. The right k is an empirical tradeoff, not a default of 5. Here is how to find it.

A 90% eval score and angry users at the same time means your eval set doesn't look like reality. The fix is to make evaluation track production, not the other way around. Here is how.

A single embedding can't represent a question with three independent parts. The signal is knowing when to split a query, how to retrieve and recombine per sub-query, and the latency and drift costs that make decomposition a net loss on simple questions.

HyDE generates a fake answer to embed, which helps on vague queries but actively hurts on factual or out-of-domain ones. The signal is naming exactly when the hypothetical document misleads retrieval and which multi-draft and hybrid variants recover.

An LLM can cite a source that does not say what the answer claims. The signal is checking claim-by-claim entailment against the cited text, not just that a citation marker exists, and knowing what to do when grounding fails.

Agents re-send growing context every step, so cost scales worse than linearly. The signal is knowing where the tokens go and the levers (caching, model routing, context trimming, step caps) that cut the bill.

The coding round version of the RAG question every candidate can describe in prose. Embed, index, retrieve, generate, cite. What separates a pass from a fail is the branch you write for when retrieval comes back with nothing worth quoting.

Every LLM product streams, and almost nobody can write the server. The interesting part is not the async generator, it is what happens when the user hits stop, the provider dies at token 90, or moderation flags text you have already put on the screen.

The modern agentic system-design question. The signal is the plan, search, read, synthesize, verify loop with per-claim citations, plus bounding cost and latency. The hard parts are not the writing.

Exact-match caching barely helps when no two prompts are identical. Semantic caching reuses answers for similar queries, and its whole risk is returning a near-match that's subtly wrong. Here is how to build it safely.

Eyeballing a few outputs does not scale, and a prompt tweak that fixes one case quietly breaks ten. A real LLM eval pipeline is a versioned dataset, layered scorers, and a CI gate. Here is the architecture.

A shared system prompt gets re-prefilled on every request unless the server remembers it. Prefix caching skips that work, but only when the blocks line up exactly. Here is the hashing and eviction machinery underneath.

GPU memory runs out long before you run out of conversations to cache. Offloading KV to CPU or NVMe buys capacity, but the interconnect can become the new bottleneck. Here is the bandwidth math.

Chasing every new model is as bad as ignoring them all. Interviewers want a repeatable filter for signal versus hype, and the discipline to evaluate on your own problem. Here is that filter.

Almost everyone can quote softmax(QKᵀ/√d_k)V. The interviewer wants the variance argument and the exact training failure the scale prevents. Here is the answer that separates memorization from understanding.

The single most-asked applied GenAI question, and the one most candidates answer as a definition dump. The interviewer wants a decision framework with a default and the conditions that flip it. Here is the call that scores.

The modal Applied AI design round. Anyone can draw embed-retrieve-generate. The signal is in chunking, hybrid retrieval, the rerank/latency tradeoff, and how you prove it works. Here is the structure that scores.

The trap is jumping straight to 'add more GPUs.' The signal is profiling first, then applying the cheap, no-retrain levers in the right order. Here is the diagnosis-then-optimize playbook for p99.

MoE is why some frontier models have huge parameter counts but serve cheaply. The signal is the sparse-activation idea, the routing mechanism, and the operational cost (memory, load balancing) that the FLOP savings quietly hide.

These are the knobs every LLM product tunes, and the interviewer wants to know what each does to the probability distribution and which setting fits which task. Including why factual and creative tasks want opposite settings.

Agents are over-applied. The strong answer resists the hype: most tasks want a single structured call, and agents earn their cost only under specific conditions. Here is when to reach for one and how to stop it from compounding errors.

The two knobs that make or break a RAG system, and the ones candidates hand-wave. The signal is tuning chunking against recall and knowing exactly what dense retrieval misses that BM25 catches. Here is the reasoning, not the rules of thumb.