Salesforce AI Engineer interview questions

Summarization is the one task where the model was handed everything it needed and still made something up. The signal is separating intrinsic from extrinsic hallucination, knowing why ROUGE cannot see either, and gating on entailment before you ship.

Real tools time out, rate-limit, and hand back malformed JSON. An agent that assumes every call succeeds is a demo, not a product. Here is the error-handling layer that keeps it running in production.

Frameworks promise speed and hand you abstraction you'll eventually fight. Rolling your own is more code but full control. Here is the honest tradeoff, and why many production teams end up thinner than they started.

Vector search over rows is the wrong tool when the user asks for a count or an aggregate. Interviewers want to see you retrieve the right schema, generate validated SQL, and know when to query the database instead of embedding it.

Multi-agent systems coordinate through handoffs and shared state. The signal is knowing the orchestration topologies, what a clean handoff protocol carries, and why naive multi-agent often loses to a single good agent.

Autonomous agents still need humans at the right moments. The signal is designing checkpoints: where to interrupt, what to surface, how to persist and resume state, without reducing the agent to a click-through rubber stamp.

The CRM says the balance is $0 and the ledger says $412. An agent left to its own devices will average them into something confident and wrong. Designing the precedence before the model has to guess is the whole answer.

Interviewers ask about these by name and listen for whether you have read the source or only the README. The signal is explaining the runnable interface, why an agent needs a cyclic graph rather than a chain, and what the layers hide.

A proactive agent runs on a trigger, with no human watching at the moment of action. That inverts the risk model, and the interviewer is listening for whether you separate notifying from acting.

This code runs on every single response, so it sits on the critical path and a heavyweight check here doubles your p95. The signal is in the ordering, the fail-open decision when the guardrail times out, and the fact that you cannot un-send a token you already streamed.

Support is the flagship applied-AI use case, exercising agents, RAG, tools, and the critical human handoff. The signal is knowing when to answer, when to take action, and when to escalate, safely.

A high-AUC churn model that changes no behavior is worthless. The strong answer nails the label definition, chooses classification vs survival deliberately, and is judged on retention uplift, not accuracy.

Reps only have so many hours, so the model exists to steer them toward the leads worth calling. Interviewers listen for value-weighted prioritization, carefully built conversion labels, and evidence of revenue uplift measured against a holdout.

When prompts live inside source code, every wording tweak becomes a full deploy and nobody knows which prompt is running. The fix is to treat prompts as managed, versioned configuration. Here is the platform.

Hand every team an LLM API key and your bill turns into a mystery capped by a six-figure surprise at month end. Attributing, capping, and optimizing spend is a platform feature. Here is how to build it.

An AI support agent working through millions of chats will occasionally be wrong, rude, or unhelpful, and no one can read them all. Watching quality at that scale is a design problem in itself, with its own failure modes.

Auto-resolving support tickets means grounding answers in your knowledge base, safely calling real APIs (refunds, account changes), and knowing when to hand off to a human. Learn the agent loop, the guardrails, and how to measure resolution without eroding trust.

Agents that loop for minutes, invoke tools, and spawn sub-tasks demand durable execution rather than one request handler. See how to checkpoint state, recover after failures, cap runaway loops, and trace every move a non-deterministic agent makes.

Five thousand businesses, five thousand assistants, one platform. The hard parts are tenant isolation you can defend, noisy neighbors, onboarding a tenant with zero data, and evaluating assistants you can never manually QA. Here is the control plane and the data plane.

Promotion is the easy part. Governance covers who may ship what, on whose sign-off, with what documented, and how a model gets retired. Here is the control plane an auditor actually asks for.

An enterprise RAG that retrieves across everyone's documents is a breach in waiting. The fix belongs in the retrieval layer, not the prompt. Here is the design that survives a security review.

LLM apps bleed secrets in three quiet places: the prompt, the logs, and the next training set. Each demands a different control. Here is how to close all three.

AI features create cross-tenant leak paths that classic SaaS isolation never had to reckon with: shared embeddings, shared caches, and fine-tunes that memorize. One leak ends an enterprise contract. Here is the isolation model.

Adopting a vendor model pulls their data practices, security, and failure modes into your product. The signal is a structured assessment spanning data handling, security, performance, and contractual terms, not just a demo that looked good. Here is the answer.

An agent running on a single over-privileged service account is a confused deputy waiting to happen. The signal is per-user delegated credentials, token exchange, per-tool scopes, and an audit trail that names the human. Here is the answer.

AI features are probabilistic, yet stakeholders hear 'it works.' Setting honest expectations without draining enthusiasm is a core applied-AI skill. Here is how to frame reliability so trust holds through the first mistake.

Hype primes customers to expect a system that reads minds and never fails. Resetting that without losing the deal is an applied-AI skill interviewers probe head-on. Here is the move.

AI features break in public, sometimes embarrassingly. How you respond to the customer, not only the bug, is what this question actually tests. Here is the recovery that rebuilds trust.

The model can be excellent and still fail if the people who must use it do not trust it. Adoption is change management, not a slicker demo. Here is how forward-deployed engineers actually earn it.

An angry customer tests composure and ownership, not empathy alone. Interviewers want to watch you de-escalate, fix the real problem, and rebuild trust. Here is the arc that scores.

Scope creep quietly sinks deployments and erodes trust on both sides. Interviewers want to see you defend the timeline without turning into the team that says no to everything. Here is the move.

Distributed, cross-cultural work is the norm for customer-facing AI roles. Interviewers want to see deliberate async habits and cultural awareness, not heroics. Here is what scores.

Executives buy outcomes and care about risk, not your architecture. Interviewers want to see you open with the decision, quantify in their terms, and raise risk honestly. Here is the pattern.

When everything is urgent, the skill is a defensible triage plus honest communication to whoever loses out. Interviewers want a framework and the nerve to say no clearly. Here is the move.

Vague asks are standard in customer-facing AI work. Interviewers look for structured discovery that surfaces the real problem and a measurable first win, not a rush to build. Here is the method.

Building it is not the same as adopting it. Interviewers look for you to win a beachhead, prove value, and let advocates spread it, not mandate usage from the top. Here is the playbook.

Rescuing a churning account is diagnosis under pressure: find the real reason, fix what you can, and win back trust with action. Interviewers look for a method, not a discount. Here is the move.

Security and compliance teams are gatekeepers, not adversaries. Interviewers look for you to bring them in early, satisfy real requirements, and turn a blocker into an ally. Here is the approach.

Telling a customer no is a relationship skill: shield them from a bad outcome while keeping their trust. Interviewers look for the reason, the alternative, and the framing. Here is the move.