What is Artificial Intelligence?
AI FundamentalsAIFundamentals
What is Machine Learning and how does it differ from traditional programming?
Machine LearningMachine LearningML
What is supervised learning?
Machine LearningSupervised Learning
What is overfitting and how can you reduce it?
Machine LearningOverfittingGeneralization
What is a train-validation-test split?
Machine LearningEvaluationData Split
What is precision, recall and F1 score?
Machine LearningMetricsClassification
What is a neural network?
Deep LearningNeural NetworksDeep Learning
What is an embedding?
Generative AIEmbeddingsVectors
What is a Transformer?
Generative AITransformerLLM
What is attention in a Transformer?
Generative AIAttentionTransformer
What is an LLM?
Generative AILLMGenerative AI
What is tokenization?
Generative AITokenizationLLM
What is inference?
Generative AIInferenceServing
What is Retrieval-Augmented Generation?
Generative AIRAGLLMGrounding
What is a vector database and why is it useful for RAG?
Generative AIVector DatabaseRAG
What is semantic search?
Generative AISemantic SearchEmbeddings
What is prompt engineering?
Generative AIPrompt EngineeringLLM
What is function calling or tool use in an LLM application?
Generative AIFunction CallingToolsAgents
What is an AI agent?
Agentic AIAI AgentsAgentic AI
What is the difference between an LLM application and an agentic system?
Agentic AIAgentsLLM Applications
What is hallucination in generative AI?
Generative AIHallucinationReliability
How would you reduce hallucinations in a production RAG system?
Generative AIRAGHallucinationEvaluation
What is chunking in RAG?
Generative AIChunkingRAG
What is hybrid search?
Generative AIHybrid SearchRAG
What is fine-tuning and when would you choose it over RAG?
Generative AIFine-TuningRAG
What is model evaluation in an AI application?
AI EngineeringEvaluationAI Quality
What is an evaluation dataset and why must it be representative?
AI EngineeringEvaluation DatasetTesting
How would you evaluate a RAG application?
AI EngineeringRAG EvaluationEvaluation
What is latency in an AI application and what affects it?
AI EngineeringLatencyPerformance
What is model serving?
AI EngineeringModel ServingDeployment
What is MLOps?
AI EngineeringMLOpsMachine Learning
Why is observability important for production AI systems?
AI EngineeringObservabilityProduction AI
How should secrets and API keys be handled in an AI application?
AI EngineeringSecurityAPI KeysSecrets
What is prompt injection and how can an AI engineer mitigate it?
AI SecurityPrompt InjectionAI Security
What is responsible AI?
AI GovernanceResponsible AIGovernance
How would you design a production AI service for reliability?
AI SystemsSystem DesignReliabilityAI
How do you control the cost of an LLM application?
AI EngineeringLLM CostOptimization
What is the difference between deterministic software testing and AI evaluation?
AI EngineeringAI TestingEvaluation
How would you version prompts, models and evaluation datasets?
AI EngineeringVersioningMLOpsEvaluation
Describe an end-to-end architecture for an enterprise AI assistant.
AI SystemsSystem DesignEnterprise AIAI Assistant
What is unsupervised learning?
Machine LearningUnsupervised Learning
What is reinforcement learning?
Machine LearningReinforcement LearningRL
What is a loss function in machine learning?
Machine LearningLoss FunctionTraining
What is gradient descent?
Deep LearningGradient DescentOptimization
What is regularization and why is it useful?
Machine LearningRegularizationGeneralization
What is data leakage in machine learning?
Machine LearningData LeakageML Quality
What is cross-validation and when is it useful?
Machine LearningCross ValidationEvaluation
What is a confusion matrix?
Machine LearningConfusion MatrixClassification
What is calibration in a machine learning model?
Machine LearningCalibrationProbabilities
What is model drift?
AI OperationsModel DriftMLOps
What is data drift?
AI OperationsData DriftMLOps
What is batch inference versus online inference?
AI EngineeringInferenceBatchOnline
What is quantization in model deployment?
AI EngineeringQuantizationInference Optimization
What is model distillation?
Generative AIDistillationModel Optimization
What is temperature in text generation?
Generative AITemperatureDecodingLLM
What are top-k and top-p sampling?
Generative AISamplingDecodingLLM
What is a context window?
Generative AIContext WindowLLM
How can an AI application handle context-window limits?
Generative AIContext WindowRAGOptimization
What is structured output from an LLM?
Generative AIStructured OutputJSONLLM
Why should LLM output be validated before being used by application code?
AI EngineeringValidationLLM SecurityStructured Output
What is grounding in generative AI?
Generative AIGroundingRAG
What is reranking in a retrieval pipeline?
Generative AIRerankingRAG
What is query expansion in search or RAG?
Generative AIQuery ExpansionRAGSearch
How would you prevent a RAG system from retrieving unauthorized information?
AI SecurityRAG SecurityAuthorizationData Access
What is retrieval recall in a RAG system?
AI EvaluationRetrieval RecallRAG Evaluation
What is groundedness or faithfulness in LLM evaluation?
AI EvaluationGroundednessFaithfulnessRAG Evaluation
What is human-in-the-loop AI?
AI SystemsHuman-in-the-LoopAI Safety
When should an AI system refuse to answer or take an action?
AI SafetyRefusalGuardrailsAI Safety
What are guardrails in an AI application?
AI SafetyGuardrailsAI Safety
How would you secure an AI agent that can call business APIs?
AI SecurityAgent SecurityTool SecurityLeast Privilege
What is agent memory?
Agentic AIAgent MemoryAgents
What is the difference between short-term and long-term agent memory?
Agentic AIAgent MemoryState Management
What is an agent orchestration pattern?
Agentic AIAgent OrchestrationAgents
How can you prevent an agent from entering an infinite tool-use loop?
Agentic AIAgent ReliabilityLoop Prevention
What is model routing in an AI platform?
AI SystemsModel RoutingAI Platform
How would you design a model fallback strategy?
AI SystemsFallbacksReliabilityModel Routing
What is caching in an LLM application and what should be cached carefully?
AI EngineeringCachingLLM Optimization
What is rate limiting and why is it important for AI APIs?
AI EngineeringRate LimitingAPI Security
What is multi-tenancy in an enterprise AI application?
AI SystemsMulti-TenancyEnterprise AI
How would you design tenant isolation for RAG data?
AI SecurityRAGMulti-TenancyData Isolation
What is prompt versioning and why does it matter?
AI EngineeringPrompt VersioningMLOps
What is an AI evaluation baseline?
AI EvaluationEvaluation BaselineAI Quality
How would you test an AI application before production release?
AI EngineeringAI TestingRelease Engineering
What is canary deployment for an AI service?
AI OperationsCanary DeploymentMLOps
What is shadow deployment for an AI model?
AI OperationsShadow DeploymentModel Evaluation
What is a feature store and when is it useful?
Machine LearningFeature StoreMLOps
What is a data pipeline in an AI system?
AI EngineeringData PipelineAI Engineering
Why is data lineage important in AI systems?
AI GovernanceData LineageAI Governance
How would you handle personally identifiable information in an AI pipeline?
AI SecurityPIIPrivacyAI Security
What is explainability in AI engineering?
AI GovernanceExplainabilityResponsible AI
What is bias in an AI system and how can it be assessed?
AI GovernanceBiasFairnessResponsible AI
What is AI red teaming?
AI SecurityAI Red TeamAdversarial Testing
How would you test an AI system for prompt injection?
AI SecurityPrompt InjectionRed TeamAI Security
What is an AI system's threat model?
AI SecurityThreat ModelingAI Security
What is an AI gateway or model gateway?
AI PlatformAI GatewayModel GatewayAI Platform
How would you design an AI platform for multiple model providers?
AI PlatformAI PlatformMulti-ProviderModel Gateway
What is GPU utilization and why does it matter for AI workloads?
AI InfrastructureGPUAI InfrastructureOptimization
How would you choose between self-hosting a model and using a managed model API?
AI ArchitectureModel HostingManaged APIsArchitecture
How would you design an end-to-end AI feature from prototype to production?
AI EngineeringAI Product EngineeringProduction AISystem Design
How would you design a world-class production AI engineering lifecycle?
AI SystemsAI EngineeringMLOpsSystem DesignProduction AI