System Design & Production Engineering is a core part of the EY Forward Deployed Engineer loop. Palantir-style decomposition, productionizing POCs, debugging customer incidents, observability, VPC/air-gapped deploys: where demos become deployments. Below are the system design & production engineering questions to prepare, the ones tagged to EY first, then the highest-signal questions from our System Design & Production Engineering track, each with an answer written to a senior-engineer bar.

System Design & Production Engineering questions tagged to EY

More System Design & Production Engineering questions for EY's loop

The highest-signal system design & production engineering questions candidates rate most useful, modeled on what EY's Forward Deployed Engineer loop tests.

Concepts behind EY's System Design & Production Engineering round

The vocabulary and mental models these questions assume. Start with the foundations free; the deeper, interview-defining ideas are part of premium.

FoundationalFrom Proof-of-Concept to ProductionA notebook that answered one question correctly during a demo is not a deliverable. Production is the unglamorous work that turns a one-time success into a system the customer can run, trust, and operate without you in the room. Closing that gap is most of the FDE job.

CoreSign inAI Cost and Unit EconomicsUnit economics is the napkin math that decides whether an AI deployment ships: cost per request driven by input and output tokens, multiplied by volume, against the human or manual baseline it replaces. It also governs the API-versus-self-host break-even, which only flips in favor of your own GPUs above a real utilization threshold.

FoundationalRetries, Exponential Backoff and JitterWhen a call fails on a transient error, retrying immediately is the worst thing you can do: it piles load onto an already-struggling service and synchronizes every client into a stampede. Exponential backoff spaces retries out, and jitter de-synchronizes the clients so they stop arriving in lockstep.

CoreSign inIdempotencyAn idempotent operation produces the same end state whether you apply it once or five times, which is exactly what you need in a world where retries and at-least-once delivery mean every request may arrive twice. Without it, a single lost response turns one charge into two; with it, the duplicate is a no-op.

CoreSign inRate LimitingRate limiting caps how fast a client or your whole fleet can hit a resource, so a burst of traffic or one runaway caller cannot melt a fragile downstream service or burn your third-party API quota. The interesting part is enforcing it across many machines without a race, and deciding whether to reject or queue when the limit hits.

CoreSign inObservability for AI SystemsYou cannot operate what you cannot see, and an AI system has failure modes a normal service does not: the prompt, the retrieved context, the model output, and the slow drift in quality over time. Observability for AI means logging and tracing every stage of the chain with a shared request ID, so when an answer is wrong you can reconstruct exactly why.

CoreSign inLatency OptimizationMeasure p50, p95, and p99 before you touch anything, then find where the time actually goes: tokenization, retrieval, inference, or post-processing. A naive RAG pipeline that takes 1.5 seconds can usually reach sub-100ms perceived latency by caching, parallelizing retrieval, picking a smaller model, and streaming the first token, in that order of payoff.

Advanced🔒 PremiumVPC and Air-Gapped DeploymentLarge enterprises will not let their data leave their security boundary, so you deploy your software inside the customer's private VPC, reach their data over PrivateLink instead of the public internet, authenticate through their SSO, and encrypt everything at rest and in transit. For air-gapped environments you ship self-hosted models too. This is core Forward Deployed Engineer work.

EY's Forward Deployed Engineer loop draws system design & production engineering questions such as "Orchestrate a multi-agent system over a 500-page merger agreement to produce a redlined risk summary that never contradicts the source.", "Your agent abstains on 8% of cases and every one becomes a human's problem. Design the escalation system.", "What's the difference between at-least-once and exactly-once delivery, and why should an FDE care?". Palantir-style decomposition, productionizing POCs, debugging customer incidents, observability, VPC/air-gapped deploys: where demos become deployments. The full set, ordered easy to hard with expert answers, is below.

Work the system design & production engineering questions on this page in order, study the underlying concepts linked below, then review EY's full interview process for how this round fits the loop.

Yes. EY announced Forward Deployed Engineer roles for the UK and Ireland in April 2026 and posts Forward Deployed AI Engineer roles in the US, including at associate director level.

Building AI systems inside client environments on an engagement footing rather than shipping a product. At a firm this size that also means working within procurement, risk and audit constraints that a startup deployment never encounters.

Other EY interview rounds

The other tracks EY's Forward Deployed Engineer loop tests.

Prep the whole EY Forward Deployed Engineer loop

System Design & Production Engineering is one round. Unlock every answer across EY's full loop with Premium. Free questions in every track let you try the depth first.

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Independent and not affiliated with EY. All trademarks belong to their owners.