Search problems

Loading…

Practice for AI, ML and GenAI engineering interviews. Answer out loud or in writing, then learn from the reference solution.

Start practicing

Practice

All problems
Easy warm-ups
Hard challenges
System design

Your space

Dashboard
Saved problems
Privacy
Terms
Report a problem

Account

Create free account
Log in

Loading…

AI/ML811 HR123 SQL16

Question bank

AI/ML Technical questions on LLMs, RAG, deep learning, MLOps and system design.811 HR Behavioural and HR questions, each with an expert answer you can learn from.123 SQL SQL questions with every possible answer and how to optimise each one.16

Filter by company ProSee which companies asked what.

AI, ML and GenAI interview questions

Pace planner

How fast do you want to finish?

Pace planner

The library has 811 questions. Pick a daily target.

Your own target

4 / day

150 per day

At 4 questions a day

203days

~6.7 months to finish everything

811 left ÷ 4 per day = 203 days

Done by

Per week

28 questions

Compare quick targets

of 811

Solved

Your progress

0% done

Easy
0/224
Medium
0/390
Hard
0/197

Search problems

Filters

Difficulty

Type

Access

DifficultyProblem typePro or free

47 problems

See how often each question is asked, and which companies asked it.Part of Buncho Pro.Unlock

TitleTopicTypeAsked Companies Level

Not started1.MMLU, HumanEval, GSM8K BenchmarksMedium

LLM Evaluation and Testing

Conceptual

Pro feature

Medium

Not started2.Offline vs Online EvaluationEasyLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureEasy

Not started3.Statistically Rigorous Model ComparisonHardLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureHard

Not started4.Human Evaluation of AIMediumLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureMedium

Not started5.Eval Set Does Not Match Production QueriesMediumLLM Evaluation and TestingLLM Evaluation and TestingCase studyPro featurePro featureMedium

Not started6.Precision@K vs Recall@KEasyLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureEasy

Not started7.Evaluate Coding Agents (SWE-bench)HardLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureHard

Not started8.ML vs LLM EvaluationMediumLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureMedium

Not started9.Continuous Evaluation in ProductionMediumLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureMedium

Not started10.Synthetic vs Human-Annotated Eval DatasetsEasyLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureEasy

Not started11.BLEU, ROUGE and BERTScoreMediumLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureMedium

Not started12.RAG Evaluation vs LLM EvaluationEasyLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureEasy

Not started13.Evaluate Bias in LLM OutputsHardLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureHard

Not started14.Audit Reproducibility ProHardLLM Evaluation and TestingLLM Evaluation and TestingCase studyPro featurePro featureHard

Not started15.Adversarial Testing for AIMediumLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureMedium

Not started16.AI Regression Test SuiteMediumLLM Evaluation and TestingLLM Evaluation and TestingPractical exercisePro featurePro featureMedium

Not started17.Fairness Drift Monitoring ProHardLLM Evaluation and TestingLLM Evaluation and TestingCase studyPro featurePro featureHard

Not started18.LLM-as-Judge and G-EvalMediumLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureMedium

Not started19.Why Not Judge RAG by the Final Answer Only?EasyLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureEasy

Not started20.Evaluate LLM Outputs and MetricsMediumLLM Evaluation and TestingLLM Evaluation and TestingConceptualPro featurePro featureMedium

Page 1 of 3

Promote your SaaS

Reach 9,438+ AI engineers monthly.Reach 9,438+ AI and ML engineers every month, right at the top of our question library.

$5 / month →

Your banner here

Promote your SaaS

Reach 9,438+ AI engineers monthly.Reach 9,438+ AI and ML engineers every month, right at the top of our question library.

$4 / month →