AI, ML & LLMs
11 sections1 564 questions
The whole stack for building with machine learning and LLMs: training and inference frameworks, model providers and local runtimes, agent and RAG frameworks, AI coding tools, and the MLOps, evaluation and observability layer around them. Interviewers cover this area because shipping an AI feature is now an engineering problem at least as much as a modelling one.
explore
- ML Frameworks & Libraries198 questions
- PyTorch (has its own guide)37 questions
- TensorFlow35 questions
- Keras30 questions
- Scikit-learn (has its own guide)36 questions
- OpenCV36 questions
- On-Device PyTorch (ExecuTorch)12 questions
- TFLite12 questions
- LLM Providers & Models262 questions
- OpenAI35 questions
- Anthropic31 questions
- Google Gemini32 questions
- Cohere24 questions
- Mistral19 questions
- xAI5 questions
- DeepSeek19 questions
- Meta Llama34 questions
- Google Gemma7 questions
- Qwen15 questions
- Opus3 questions
- Sonnet3 questions
- OpenAI Image Generation6 questions
- Whisper6 questions
- OpenRouter17 questions
- GitHub Models6 questions
- Vertex AIempty
- Azure MLempty
- Amazon Bedrockempty
- Amazon SageMaker AIempty
- Model Hubs & Embeddings64 questions
- Hugging Face33 questions
- Sentence Transformers21 questions
- Transformers.js10 questions
- Local Model Runtimes (has its own guide)55 questions
- AI Coding Tools (has its own guide)377 questions
- Claude Code (has its own guide)188 questions
- Cursor24 questions
- Copilot28 questions
- Codex6 questions
- Gemini CLI6 questions
- Windsurf (Devin Desktop)6 questions
- Lovable6 questions
- v06 questions
- OpenClaw107 questions
- Agent & RAG Frameworks (has its own guide)258 questions
- LangChain36 questions
- LangGraph33 questions
- CrewAI36 questions
- AutoGen28 questions
- Google ADK24 questions
- Koog17 questions
- LlamaIndex35 questions
- Haystack31 questions
- RAGFlow18 questions
- AI Ops, Eval & Observability (has its own guide)121 questions
- MLOps & Model Lifecycle94 questions
- MLflow23 questions
- DVC17 questions
- Kubeflow12 questions
- Feature Store Platforms12 questions
- Model Monitoring Tooling12 questions
- SHAP12 questions
- LIME6 questions
- LLM Inference Serving99 questions
- Serving Concepts45 questions
- vLLM18 questions
- Text Generation Inference (TGI)12 questions
- NVIDIA Triton and TensorRT-LLM18 questions
- KServe6 questions
- Distributed Training Infrastructure36 questions
- DDP & Process Groups6 questions
- Sharding & Model-Parallel Engines6 questions
- Collectives & Interconnects6 questions
- Throughput Tuning & Profiling6 questions
- GPU Scheduling on Kubernetes6 questions
- Job Launch & Fault Tolerance6 questions