HardTechnicalCodingTechnical screen20 min to answer

What causes GPU out-of-memory errors during inference, and how do you respond?

1Give yourself 20 minutes

2Answer out loud, not in your head

3Then compare with the answer below

Stuck? Show a way to structure it+

01Clarify the objective, user, constraints, and acceptable failure modes.
02Structure the response around weights, KV cache, batch size, sharding.
03Compare credible alternatives and state the decision criteria.
04Finish with validation, monitoring, and what would change the decision.

Reference answer

strong answer

I would first define the outcome and acceptable error boundary. I would explicitly cover weights, KV cache, batch size, sharding. I would select an approach only after comparing quality, latency, cost, safety, and operational complexity, then validate it with representative cases and production monitoring.

weights
KV cache
batch size
sharding

Must be adapted to the interviewer’s scenario
Would benefit from concrete numbers and personal examples

alternative answer

A second valid approach is to begin with the highest-risk assumption and test it cheaply. I would explicitly cover weights, KV cache, batch size, sharding. I would select an approach only after comparing quality, latency, cost, safety, and operational complexity, then validate it with representative cases and production monitoring.

weights
KV cache
batch size
sharding

Must be adapted to the interviewer’s scenario
Would benefit from concrete numbers and personal examples

Grade yourself

weights

weight 30%

StrongExplains weights concretely and ties it to a decision or measurable outcome.

WeakMentions weights without implications, trade-offs, or evidence.

KV cache

weight 25%

StrongExplains KV cache concretely and ties it to a decision or measurable outcome.

WeakMentions KV cache without implications, trade-offs, or evidence.

batch size

weight 25%

StrongExplains batch size concretely and ties it to a decision or measurable outcome.

WeakMentions batch size without implications, trade-offs, or evidence.

sharding

weight 20%

StrongExplains sharding concretely and ties it to a decision or measurable outcome.

WeakMentions sharding without implications, trade-offs, or evidence.

Then expect these follow-ups

What assumption is most fragile?
Tests: depth
What alternative did you reject and why?
Tests: adaptability
How would you validate this in production?
Tests: adaptability

Hiring now

Machine learning engineer roles are open right now

landed applies to roles like these for you, on each company’s own site, with answers written for the role.

Get 5x interviews10 free auto-applies. No card.

AI/ML Engineer
Kaizen Labs · New York, NY
Senior ML Engineer, Perception
Clera · San Francisco
Machine Learning Engineer
Endava · Córdoba, Cordoba, Argentina

Or practice this question first

Next question