Cloudflare LLM Application Security interview questions

An easy question with a revealing follow-up. The answer that scores limits cost at every layer, including the agent loop, not just requests per minute.

Product security's favourite AI question, because the answer is mostly classic AppSec. The scored part is matching each sink to its control and preferring structured data over generated code.

The question catches candidates who think exfiltration needs a tool. The answer that scores starts with the browser and ends with deterministic controls in the client.

A design round in miniature. The answer that scores follows the data through both halves of the pipeline and spends most of its time on authorization, where real leaks happen.

Similarity search has no idea who is asking. The answer that scores makes the index enforce the source system's rules, at query time and over time.

Breadth first, then priority. The answer that scores follows one sensitive value through every copy the system makes and fixes the two that leak most.

Poisoning a knowledge base is cheaper than poisoning a model. The answer that scores starts from who can write to the corpus and limits what a poisoned chunk can achieve.

Both, plus the layer most people forget: the action boundary. The scored skill is placing each check where it sees the right thing and labelling which ones are boundaries.

An incident question disguised as debugging. The answer that scores treats it as a possible breach, preserves evidence, and checks the four usual causes in order of likelihood.

The tempting answer is that embeddings are one-way hashes. They are not. The answer that scores explains inversion and protects the index like the documents.

LLM observability quietly becomes the largest copy of customer data in the company. The scored answer minimises what is captured, separates what must be kept, and treats trace stores as production data.

There is no single answer, and saying so is the start. The scored answer decides per check from what its failure would let through, and designs the latency budget so the choice is rarely forced.

A guardrail that blocks everything scores perfectly on attacks. The scored answer measures both errors, tests with attacks the guardrail has not seen, and reports with intervals at the operating threshold.

Caches are shared state, and shared state crosses tenants. The scored answer separates response caches from prompt prefix caches and keys each so one user can never read or detect another's data.

Fine-tuning moves data from a database you can query and delete into weights you cannot. The scored answer covers memorisation, tenant separation, poisoning and the deletion problem.

When people act on wrong output, the harm is real even though nothing was hacked. The scored answer names the concrete failures and designs the product so verification is easy and required where it matters.