Concept
AI system design
Architecting LLM applications: serving, retrieval, caching, guardrails and scaling.
Learn firstLLMs
AI system design
What should you learn before AI system design?
- Deep learningMachine learning with many-layered neural networks.
- Tokens and tokenizationSplitting text into the units a language model reads and is billed by.
- TransformersThe attention-based neural network architecture behind modern language models.
- Large language models (LLMs)Transformer models trained on large amounts of text to predict the next token.
Connections to other concepts
- Includes
- CachingLLM inference and costRAG
- Related
- Technical interviews