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
Blog

Your space

Dashboard
Saved problems
Privacy
Terms

Account

Create free account
Log in

Loading…

Generative AI and LLMs Interview Questions (Page 3) | Buncho

Library Dashboard Saved for later

Topics

Python for AI/ML75 Machine Learning Fundamentals10 ML Algorithms0 ML System Design1 Deep Learning5 Statistics and Mathematics1 Generative AI and LLMs122 Embeddings13 RAG and Vector Databases47 AI Agents and Tool Calling50 MCP0 Multimodal AI29 LLM Evaluation and Testing27 AI Safety, Ethics, and Responsible AI36 AI System Design41 Fine-Tuning25 AI Infrastructure and Scalability29 LLM Gateways0 Production AI Engineering39 AI Engineering Case Studies15

of 565

Solved

Easy0/73
Med.0/297
Hard0/195

Topic

Generative AI and LLMs interview questions

Transformers, prompting, and LLM behaviour.

All topics565 Python for AI/ML75 Machine Learning Fundamentals10 ML Algorithms0 ML System Design1 Deep Learning5 Statistics and Mathematics1 Generative AI and LLMs122 Embeddings13 RAG and Vector Databases47 AI Agents and Tool Calling50 MCP0 Multimodal AI29 LLM Evaluation and Testing27 AI Safety, Ethics, and Responsible AI36 AI System Design41 Fine-Tuning25 AI Infrastructure and Scalability29 LLM Gateways0 Production AI Engineering39 AI Engineering Case Studies15

Search problems

DifficultyProblem type

122 problems

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

TitleTopicTypeTimeAsked Companies Level

Not started41.Your RLHF-trained LLM is gaming the reward model instead of being genuinely helpful. How do you fix reward hacking?Generative AI and LLMs · Debugging · 10 min

Asked %

Companies

Generative AI and LLMs

Debugging

10 min

Pro feature

Hard

Not started42.Explain zero-shot, one-shot and few-shot prompting with examplesGenerative AI and LLMs · Conceptual · 8 minAsked %CompaniesGenerative AI and LLMsConceptual8 minPro featurePro featureEasy

Not started43.Why do we scale dot-product attention by the square root of d_k?Generative AI and LLMs · Conceptual · 10 minAsked %CompaniesGenerative AI and LLMsConceptual10 minPro featurePro featureMedium

Not started44.Your LLM classification system is too sensitive to prompt wording changes. How do you reduce prompt sensitivity?Generative AI and LLMs · Debugging · 10 minAsked %CompaniesGenerative AI and LLMsDebugging10 minPro featurePro featureMedium

Not started45.Explain Direct Preference Optimization (DPO)Generative AI and LLMs · Conceptual · 10 minAsked %CompaniesGenerative AI and LLMsConceptual10 minPro featurePro featureHard

Not started46.What is self-attention, and how does it work in Transformers?Generative AI and LLMs · Conceptual · 12 minAsked %CompaniesGenerative AI and LLMsConceptual12 minPro featurePro featureMedium

Not started47.What is a prompt template, and how do you design one for production use?Generative AI and LLMs · Practical exercise · 10 minAsked %CompaniesGenerative AI and LLMsPractical exercise10 minPro featurePro featureMedium

Not started48.What is Grouped-Query Attention (GQA), and how does it differ from Multi-Head Attention?Generative AI and LLMs · Conceptual · 8 minAsked %CompaniesGenerative AI and LLMsConceptual8 minPro featurePro featureMedium

Not started49.How do Diffusion Language Models (DLMs) work?Generative AI and LLMs · Conceptual · 10 minAsked %CompaniesGenerative AI and LLMsConceptual10 minPro featurePro featureHard

Not started50.How do you optimise prompts for cost and latency?Generative AI and LLMs · Practical exercise · 10 minAsked %CompaniesGenerative AI and LLMsPractical exercise10 minPro featurePro featureMedium

Not started51.What is the difference between GPT and BERT?Generative AI and LLMs · Conceptual · 7 minAsked %CompaniesGenerative AI and LLMsConceptual7 minPro featurePro featureMedium

Not started52.Why is the first token slower than the rest in an LLM?Generative AI and LLMs · Conceptual · 10 minAsked %CompaniesGenerative AI and LLMsConceptual10 minPro featurePro featureMedium

Not started53.Explain scaled dot-product attentionGenerative AI and LLMs · Conceptual · 12 minAsked %CompaniesGenerative AI and LLMsConceptual12 minPro featurePro featureMedium

Not started54.Your KV cache grows too large during long generations. How do you manage memory?Generative AI and LLMs · Practical exercise · 10 minAsked %CompaniesGenerative AI and LLMsPractical exercise10 minPro featurePro featureHard

Not started55.Explain RMSNorm (Root Mean Square Layer Normalization)Generative AI and LLMs · Conceptual · 7 minAsked %CompaniesGenerative AI and LLMsConceptual7 minPro featurePro featureMedium

Not started56.Compare PPO, DPO and GRPO for aligning and training LLMsGenerative AI and LLMs · Conceptual · 12 minAsked %CompaniesGenerative AI and LLMsConceptual12 minPro featurePro featureHard

Not started57.Write code to detect and handle hallucinations in LLM outputsGenerative AI and LLMs · Practical exercise · 20 minAsked %CompaniesGenerative AI and LLMsPractical exercise20 minPro featurePro featureHard

Not started58.What is the difference between encoder-only, decoder-only and encoder-decoder Transformers?Generative AI and LLMs · Conceptual · 8 minAsked %CompaniesGenerative AI and LLMsConceptual8 minPro featurePro featureMedium

Not started59.How do Attention Sinks work?Generative AI and LLMs · Conceptual · 8 minAsked %CompaniesGenerative AI and LLMsConceptual8 minPro featurePro featureHard

Not started60.Explain the Query (Q), Key (K) and Value (V) in attentionGenerative AI and LLMs · Conceptual · 12 minAsked %CompaniesGenerative AI and LLMsConceptual12 minPro featurePro featureMedium

Page 3 of 7