The FDE concept map
114 concepts across 10 tracks, drawn with the 279 links between them. 81 of those links (29%) cross tracks, which is the part worth looking at: the concepts that decide FDE interviews are rarely the ones that sit neatly inside one topic. Hover a concept to see only what it touches. Click to read it.
Where the map is dense
The most-connected concepts are the ones the rest of the library keeps reaching for, which makes them the highest-leverage things to be solid on: Retrieval-Augmented Generation (RAG) (15), Golden Datasets and Eval Sets (13), Latency Optimization (12), KV Cache (11), and Inference Serving (vLLM, TGI) (11). If you are deciding where to spend a week, start with a hub rather than a leaf.
Every concept, by track
Foundations of LLMs & GenAI26
- KV Cache11
- Embeddings & Vector Representations9
- The Transformer, Intuitively9
- RLHF (Alignment)8
- Reward Models8
- The Context Window7
- Prompt Engineering7
- Why LLMs Hallucinate7
- Tokenization & Tokens6
- Temperature, Top-p and Sampling6
- Fine-tuning vs RAG vs Prompting6
- Direct Preference Optimization (DPO)5
- Multimodal Models and VLMs5
- Attention and Self-Attention4
- Constitutional AI and RLAIF4
- Policy Optimization: PPO and GRPO4
- Inference-Time Compute4
- RoPE and Positional Encodings3
- Constrained Decoding3
- Chain-of-Thought Prompting3
- LoRA and Parameter-Efficient Fine-tuning3
- Mixture of Experts (MoE)3
- Scaling Laws3
- Speech and Voice AI3
- Autoregressive Decoding3
- Diffusion Models2
Retrieval & Agents13
- Retrieval-Augmented Generation (RAG)15
- Vector Databases7
- Guardrails7
- Tool / Function Calling6
- Agent Memory6
- Hybrid Search (Lexical + Vector)5
- Reranking and Two-Stage Retrieval5
- Approximate Nearest Neighbor (ANN)5
- AI Agents and Tool Use5
- Chunking Strategies4
- Context Window Management for FDE Agents4
- Multi-Agent Orchestration3
- TF-IDF and BM253
Evaluation & ML Foundations23
- Golden Datasets and Eval Sets13
- Precision, Recall and F110
- Gradient Descent & Learning Rate8
- LLM-as-a-Judge8
- A/B, Canary and Shadow Testing8
- Bias-Variance Tradeoff7
- Information Theory for ML: Entropy, Cross-Entropy, KL and Perplexity6
- Overfitting and Regularization6
- Offline vs Online Evaluation6
- Evaluating RAG Systems5
- Calibration and Uncertainty4
- Synthetic Data Generation4
- Benchmarks and Their Limits4
- Catastrophic Forgetting3
- Loss Functions3
- Activation Functions3
- Neural Network Basics: Perceptron to MLP3
- Semi-Supervised and Self-Training3
- Computer Vision: Classification, Detection, Segmentation3
- Multi-Armed Bandits2
- Normalization: Batch vs Layer2
- Handling Imbalanced Data2
- Convex vs Non-Convex Optimization2
The map is for orientation. If you would rather be told what to do in order, the start-here path sequences the same material by background and stage, and the courses walk it front to back.