AI engineering study topics
Explore 205 interview questions across 10 topics. Start with LLM fundamentals, then work through agentic workflows, retrieval, evaluation, and production systems.
LLM Fundamentals
Core architectures, Transformer mechanics, self-attention, context windows, tokenization, KV cache, and sampling algorithms.
20 questions · Beginner to advanced
Prompt Engineering
Zero/few-shot, Chain-of-Thought (CoT), Tree-of-Thoughts, ReAct, system prompts, structured JSON outputs, and injection defense.
20 questions · Beginner to advanced
RAG & Vector Databases
Embeddings, vector indexing (HNSW, IVFFlat), hybrid search, chunking strategies, re-ranking, and query transformation.
20 questions · Beginner to advanced
AI Agents & MCP
Agentic workflows, Model Context Protocol (MCP), function calling, tool use, memory persistence, and multi-agent orchestration.
20 questions · Beginner to advanced
Fine-Tuning & Adaptation
PEFT, LoRA, QLoRA, RLHF, DPO, GRPO, quantization (GGUF, AWQ, GPTQ), model distillation, and domain adaptation.
20 questions · Beginner to advanced
AI System Design
High-throughput inference, TTFT/TPOT, streaming (SSE), semantic caching, GPU resource planning, and serving infrastructure (vLLM, TGI).
20 questions · Beginner to advanced
LLMOps & Production AI
Observability, prompt tracing, cost management, drift detection, CI/CD pipelines for prompts & evals, and production telemetry.
20 questions · Beginner to advanced
Evaluation & Testing
LLM-as-a-Judge, Ragas metrics (Faithfulness, Relevance), benchmarks (MMLU, HumanEval), unit testing, and red teaming.
20 questions · Beginner to advanced
AI Safety & Governance
Data privacy, PII masking, guardrails (NeMo, Llama Guard), alignment tax, copyright, and responsible AI deployment.
25 questions · Beginner to advanced
Interview Experience
Role-specific interview blueprints (AI Engineer, FDE, AI Architect), portfolio project presentation, and scenario checklists.
20 questions · Beginner to advanced