Skip to content
AI-grafen
Sign in
☰ Menu

The goal F AI engineering

AI in production

Serving, scaling, distributed systems, operations and calibrated uncertainty — plus a project where you deliver a service that holds up.

Knowledge nodes
80
From zero
about 71 h
Labs
6
See what you already know — no account

The diagnostic removes what you already know, so your path is usually much shorter.

What you can do afterwards

Labs along the way

You write the code. Tests you cannot see decide whether it holds up.

Lab: build an eval harnessEa sandbox · about 60 minLab: a neural network in pure NumPy — forward, backprop, gradient checkDa sandbox · about 75 minLab: dot product, norm and cosine similarityDin the browser · about 40 minLab: gradient descent from scratchDin the browser · about 50 minLab: matrix multiplication and one layer of a neural networkDin the browser · about 45 minLab: scaled dot-product attention with a causal maskDa sandbox · about 60 min

The whole path

Everything the goal builds on, grouped by level and in the order it builds on itself. Show on the map

AExplorer2 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
BInvestigator6 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Source criticism and responsibility in AI use
  5. Training data, features and labels
  6. Classification: how a model sorts information
CBuilder12 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Python — strings and text processing
  6. Python — files, CSV and JSON
  7. Statistics — mean, median and spread
  8. Probability — the basics
  9. Linear regression: fitting a straight line to data
  10. Neural networks — the intuition
  11. Prompting — steering a language model
  12. Responsible use of AI
DAI developer30 knowledge nodes
  1. Derivatives and optimisation
  2. Python — functions, scope and exceptions
  3. Python — classes and objects
  4. Python — modules, packages and virtual environments
  5. Git — version control
  6. APIs and HTTP
  7. Licences and open data
  8. Probability distributions
  9. Loss functions
  10. The terminal and the shell
  11. Testing with pytest
  12. Tokenisation
  13. Gradient descent
  14. The context window, system prompts and few-shot
  15. Vectors
  16. Matrices and matrix multiplication
  17. Linear regression with several features
  18. Neural networks — the forward pass with matrices
  19. Backpropagation
  20. Embeddings — words as vectors
  21. Attention
  22. NumPy — arrays and vectorisation
  23. Overfitting and generalisation
  24. Pandas — tables in Python
  25. PyTorch — tensors and autograd
  26. Retrieval — finding the right text
  27. SQL — the basics
  28. Training, validation and test
  29. Train a neural network in PyTorch
  30. Transformers — the architecture
EUniversity20 knowledge nodes
  1. Asynchronous programming
  2. Building an API with FastAPI
  3. Networking — the basics
  4. Personal data and anonymisation
  5. The GDPR and AI
  6. Docker — containers
  7. Data pipelines and ETL
  8. Data versioning
  9. Multi-head attention in detail
  10. The KV cache
  11. Latency, throughput and batching in inference
  12. Language models — training and generation
  13. Model evaluation
  14. Build an eval harness
  15. From prototype to product
  16. Observability for ML systems
  17. RAG — retrieval-augmented generation
  18. Prompt injection
  19. Tool use
  20. Agents — plan, act, observe
FAI engineering10 knowledge nodes
  1. Distributed systems — the basics
  2. MLOps: deployment, versions, rollback
  3. Serving and scaling models
  4. Calibration and uncertainty in models
  5. Data drift and model decay
  6. Project: build an AI service end to end
  7. Evals for language models and agents
  8. AI safety and red teaming
  9. Jailbreaks and guard rails
  10. A security review before launch