NexForay

Learn Interview Roadmap Resources

Interview SkillsLLMs

What is a large language model? What is a context window? What is temperature? What is prompt engineering? What is fine-tuning? What is instruction tuning? How do you reduce hallucinations in an LLM application? Why are structured outputs useful with LLMs? Foundation model vs fine-tuned — when to fine-tune vs prompt-engineer? How does autoregressive decoding work? Temperature, top-k, top-p? What is instruction tuning? How does RLHF improve on it? Explain system prompt vs user message vs assistant turn. What is context-aware prompt engineering for document extraction? How do you handle LLM hallucinations in a document extraction pipeline? How do you handle context length limitations in long-document tasks? What is LoRA fine-tuning and how does it reduce memory cost? How do you choose between Claude, GPT-4, Llama for an enterprise task? How does Ollama enable local model inference? What did you use it for?

LLMs Interview Questions

Large language model fundamentals for applied AI and Generative AI engineering roles.

18 questionsskill

Next →

Prepare for your next career move.

Learn·Interview Prep·Roadmaps·Resources

© 2026 NexForay

Built by Amit Jsr