Baseten AI Infrastructure Engineer interview questions

Derive the weight-only shortcut, then add KV traffic and feasible eight-GPU placement. A worked latency floor shows why batch size alone cannot establish the decode bottleneck.

Derive how reusing weights changes arithmetic intensity, then separate the roofline ceiling from tile-wave effects and measured GEMM throughput.

Compare the cost of serving the same workload at the same latency and quality. A memory-traffic estimate explains what each GPU might improve; measured throughput and your actual rental price determine the purchase.

Compare GPU memory, decode traffic and measured useful throughput. Work out a capacity ceiling without mistaking it for a performance forecast.

Size adapter and full-parameter jobs before comparing RTX PRO 6000 and H100. Test memory headroom, MIG packing, software support and real communication costs.

Compare ownership, colocation and rental using the same useful work, full annual costs and realistic demand. Work a break-even from explicit assumptions.

Define who owns each facility and hardware action, model restoration time, and verify power, cooling, telemetry and growth commitments before deployment.

Follow the weight bytes through a small decode batch and a long prefill. A scoped roofline calculation explains the difference without pretending to predict actual latency.

Follow a token into retained attention state, derive bytes per position for a 70B model, and distinguish present cache usage from the room needed to finish a response.

One request finishes, another keeps writing, and a third waits outside. Follow the same workload through two schedules to see what continuous batching improves, and what it cannot promise.

Trace one cache position through a block table, calculate the memory recovered from oversized reservations, and explain why sharing still needs careful writes and matching.

Work from token timestamps to first-token wait, average pace and individual stalls. Then count requests meeting both latency limits, keeping failures and measurement boundaries explicit.

Work from each GPU's cache budget, reserve room for generated tokens, then check latency separately. A limiting-rank example shows why fitting today's prompts is not enough to admit tomorrow's work.

Trace a 20,000-token prompt through a shared token budget, including the last partial chunk. Then choose a setting from measured first-token waits and streaming gaps.

Trace the slow requests through queue, engine and gateway clocks. A flat median narrows the investigation, but it does not establish a cause.

Filter engine candidates by exact compatibility, then compare correctness, goodput and operational cost on the same workload.

Forecast demand across startup delay, track replicas already being created, and drain slowly enough to avoid repeating the same scale decision.

Trace a model startup through storage, runtime setup and device loading. Transfer floors and dependencies determine whether a minute is plausible.

Trace a dropped stream through bounded queues, engine cancellation and safe resource release; define what retries and incomplete delivery mean.

Thirty percent GPU utilization means kernels ran during about thirty percent of the sampled time. Find out what limits those kernels, what happens between them, and whether requests are meeting their latency targets.

Work two audio timelines: input accumulation before transcription and playback starvation after synthesis. Compare real-time factor, response delay and safe concurrent capacity without mixing their units.

Diagnose a stream that begins quickly but produces useful answer content late. Compare generation, parser and client clocks, then test a reasoning budget without hiding truncated or incorrect responses.

Derive a deployment candidate from the official tensor index, then account for latent-cache replication and the product workload. A worked example shows why enough aggregate HBM can still leave every GPU out of memory.

Find which startup step runs out of memory, count the allocations on that GPU, and change the setting that controls the shortage.

Turn public metadata into a deployment candidate with explicit uncertainty. Inspect architecture, stored formats and engine support, then work a per-rank memory example that explains why an aggregate fit can fail.

Find whether expert placement, small batches or communication makes the deployment slower. Compare equivalent workloads and inspect the worker that holds up each step.

Measure reachable prefix reuse, separate token savings from latency, and compare both engines on the same agent contract and resource budget.

Use the actual tensor index to size Kimi K3, then separate a published hardware starting point from production capacity. Account for mixed precision, hybrid recurrent state, parser behavior, and the workload behind a throughput claim.

Check the bound’s assumptions, locate the critical path, and quantify which optimization can actually improve one user’s decode latency.

Derive a prompt-plus-output contract, calculate per-rank state capacity, and measure the concurrency that meets latency and overload targets.

The answers sound fluent, but the scores dropped. Compare inputs, generation settings, raw output, parsing and scoring to find where the new deployment differs.

Define a reproducible workload and service contract, account for every offered request, and choose a measured operating region with evidence and margin.

Compare actual encoded tensors, per-rank runtime fit, supported kernels and held-out task quality. Four-bit weight-only kernels can accelerate wider arithmetic, and smaller weights need not reduce the GPU count.

A repeated-prompt test measures one reuse pattern. Production gains depend on token-weighted reuse, routing, residency, alignment and the prefill share of latency; a falling hit rate does not uniquely identify eviction.

Long prefills coincide with decode stalls. Compare a tuned combined pool with separate phases, derive transfer and pool capacity, and test whether the improvement survives connector failures.

The output forecast is a starting point. Match the prompt and state workload, derive replica counts from an SLO-tested rate, check simultaneous loss scenarios and keep the cost denominator consistent with the forecast.

Compare committed output per complete draft-and-verify cycle with ordinary decoding. Derive the acceptance-length model, separate it from engine counters, and test latency, goodput and memory across the actual workload.

Confirm that requests are waiting for usable state capacity. Separate allocated memory, live blocks and evictable prefixes, then compare admission, lower-precision state, prefix sharing and hardware changes with explicit assumptions.

A fourfold ratio is a symptom, not a diagnosis. Trace individual requests, separate waiting from execution and delivery, and test workload, scheduling, cache and capacity hypotheses against the service objective.

Build a week around release gates and dependencies. Budget artifact transfer, validate the exact runtime path, measure the intended workload, and size the canary evidence before promising full rollout.

Price the same workload and service guarantees, including input tokens, idle capacity, failures and operations. Then check whether the algebraic crossover fits the fleet before treating it as a buying decision.

An apparent outlier can reflect workload mix, queueing, runtime state or a degraded execution path. Normalize the comparison, run a matched replay and use critical-path arithmetic to test possible causes.

A context-window limit is not a latency or concurrency guarantee. Budget retained state, prefill and shared service time; distinguish cache reuse from eliminating work; choose isolation only when measured interference justifies its cost.

A minor revision can change weights, encoding or response behavior. Compare pinned deployment bundles, evaluate task slices, monitor a representative canary and keep enough capacity to restore the old service.

Design a shared catalogue with explicit service tiers, reproducible deployments and bounded cold starts. Residency depends on burst behavior and resource reuse; placement depends on GPU groups and interference as well as memory.

Apply the project’s offline tuning guidance in context, derive the memory tradeoff, and use workload-specific acceptance criteria instead of universal queue and headroom targets.

Verify the throughput definition and service outcomes, compare resolved configurations and execution traces, then isolate supported changes. Quantify capacity replacement correctly and choose rollback from the full release risk.

Budget growing attention state, bounded recurrent state and retained prefix snapshots separately. Work the short-context crossover, then test whether the cache manager resumes every layer from the same prefix boundary.

Separate pre-routing from a sequential cascade, charge every attempted generation, and measure checker mistakes. A lower escalation rate is not proof of higher quality, and the largest model is not a correctness oracle.

Define whether half the footprint means checkpoint bytes or runtime memory. Choose a supported recipe, measure which tensors it changes, separate calibration from held-out evaluation, and validate quality and serving cost.

Follow media through fetching, preprocessing, encoding and language-model execution. Derive visual positions from the actual processor output, account for encoder placement and separate the caches and latency stages that text-only monitoring misses.

A partial drop does not rule out the parser. Define success and its denominator, trace failures through encoding, generation, parsing and execution, then replay the relevant boundary with controlled versions.

Test the complete serving bundle with contract fixtures, representative tasks and load-aware outcomes. Preserve paired results, calibrate the scorer and distinguish a relative improvement from meeting an absolute product requirement.

Constrained decoding restricts valid continuations; it does not guarantee completion or correct values. Define success and error contracts, validate supported schemas, and measure compilation, masking and queueing under the actual workload.

Attribute queueing, token work and live state before choosing a cap. Bound new admission, verify recovery, and distinguish fair scheduling, reserved service and physical isolation without promising instant or absolute protection.

Screen exact checkpoints for hard requirements, then compare deployable candidates on held-out product tasks, service limits and total cost. Smaller artifacts, leaderboard scores and token rates each answer only part of the decision.

Measure exposed launch and dispatch delay, actual graph coverage, capture memory and warmup. Batch size influences the result, but does not alone determine whether graphs improve the service.

Group compatible adapters by pinned base, derive their size from target matrices and ranks, and benchmark mixed batches. Catalogue size, CPU residency, GPU slots and active adapters are separate limits; base sharing does not make fifty variants operationally free.

A mutable branch or local model directory can change what a restarted replica loads. Establish the actual artifact identity, separate disk evidence from loaded state, and make rollout and restart behavior reproducible.

Follow a shard index to the tensors a loader actually receives. Diagnose a missing file and a shape mismatch, then check architecture, quantization and request compatibility before changing hardware.

Map a checkpoint format to compute capability, then say which part of the speedup survives on each generation. The same file can load on two GPUs and take two different execution paths.

Turn a benchmark number into a bill that survives real utilization, then write the serving contract the gateway enforces and the evaluation the tuned configuration still owes.

A measured run shows where the time goes in a small batch job, then why every result parsed but none was deliverable. The answer turns on startup cost, co-tenant latency and a per-item contract.

Walk a single-GPU vLLM Deployment from pod scheduling to the first token, then show the three settings that turn a working manifest into restart loops and stuck rollouts.

Calculate Llama 3.1 70B KV cache memory at 128k context using eight KV heads. Worked BF16 and FP8 payloads, GB versus GiB, and per-GPU capacity checks.

Check model placement first, then derive a TP8 traffic floor and add context. Separate a single stream’s pace from an ideal bandwidth ratio.

Compute cost from a matched bill and token count. Show when an activity factor belongs in the denominator and when it would double-count idle time.

Translate active streams into replicas using growth reservations and matched latency tests. Show peak and failure headroom separately, with no invented benchmark.

Derive the batch-295 shortcut, count the tensors it omits, and test whether the resulting kernel estimate is even inside the replica’s memory budget.

Use Little’s law to distinguish waiting and active requests, then test saturation with a stated service model. Avoid turning a mean occupancy identity into a universal latency rule.

Compare tensor, pipeline and expert traffic with per-request KV transfer. Work through declared payload and latency assumptions before choosing a serving network.

Define warm, cached and truly cold paths, then size transfer budgets and warm capacity without promising universal sub-second restores.

Measure scheduling, image transfer, unpacking and model initialization separately. A missing-device error needs its own checks for allocation, container access and CUDA compatibility.

Make readiness mean that the engine can serve, scale from measured demand and ready capacity, and drain streams before termination. Kubernetes can implement these controls; an operator packages and reconciles them.

Define request success, first-output latency and streaming continuity for each service class. Count bad outcomes against an explicit budget, then use paired long and short windows to detect significant ongoing degradation.

Stop rollout expansion, preserve evidence and use the safest available mitigation. Compare versions under representative load, and size canary exposure from the regression you need to detect rather than a fixed traffic percentage.

Follow a request from the client's connection pool to the first text on screen. Work the timing budget, locate a buffering delay and choose what to trace without losing the slow requests.

Compare equivalent requests, inspect the replica’s software and device state, and reduce new traffic only after checking where that load will go.

Follow one request from API admission to streamed output, then zoom into the token-generation loop. See where the cache lives, who schedules work, and how workload measurements turn the drawing into a capacity plan.

Eight ready slots meet a twelve-request burst. See why starting instances do not count as ready capacity, then design caches, isolation, admission and a measurable startup contract.

A 60-second demand ramp meets a 70-second startup delay. Compare the rate and ready-capacity curves, then design a controller that tracks pending launches without a blind cooldown.

Trace a stalled stream without unbounded telemetry, understand what sampling loses, and reconcile GPU allocation with a stated cost policy.

Implement bounded retries with full jitter, a shared credit budget and a cooperative deadline. Test repeatability and explain what a timeout leaves uncertain.

Implement size- and timer-triggered batching, then test cancellation, handler errors and the latency added before dispatch.

Build a byte-budget cache with reference-counted pins and admission that preserves existing entries when it fails.

Simulate admission, decode growth and preemption. Check memory accounting and useful progress with the same finite workload.

Implement bounded recovery probes, state-generation tickets and a recent failure window. Test concurrency and late completions.

Show a cost reduction with comparable service evidence, realized savings and a feasible recovery plan. Distinguish a quiet trial from proof of unchanged reliability.

Coordinate simultaneous incidents with the people available. Contain urgent harm, assign next actions and revisit priorities as evidence changes.

Trace GPU credits through reservation, allocation, metering and settlement, with crash-safe ownership and a separate fairness policy.

Track request admission through a concrete page-reservation example, then connect scheduling, growth and stream cleanup to measured service limits.

Derive a 10,240-GPU layout from model work, then account for collective traffic, durable checkpoints, power and replacements. A nested diagram connects tensor, pipeline and data parallel groups to the fleet.

Compare raw weight sizes at 16, 8 and 4 bits, then budget KV cache and runtime memory for Llama 3.1 70B. Follow the worked per-GPU example.

Separate quota, borrowing, reclaim latency and fairness, with a demand-conserving example of when pooling improves utilization.

Draw query-head sharing, count actual stored state and compare payloads with explicit model geometry and binary units.

Work from training FLOPs to fleet throughput, days and GPU-hours. Then see how utilization and downtime change the estimate.

Follow a four-GPU request from advertised capacity to concrete devices, and see why free GPUs across nodes cannot satisfy one pod.