Production / Knowledge book
AI Engineering
Overview
Connect models to reliable software and infrastructure.
The intelligence may come from the model. The experience comes from the engineering.
Published in this topic
01When Caching Makes an AI Answer Fast and Wrong
Design scoped, versioned answer-cache keys and invalidation rules. Learn how stale evidence, permission changes, and concurrent fills affect correctness.
Why AI Requests Wait: Bounded Queues and Deadlines
Use a worked queue example to understand overload, admission limits, deadlines, retries, and the difference between offered and successful throughput.
Why More AI Replicas Do Not Immediately Fix a Spike
Trace demand through an autoscaling controller, provisioning, model startup, and readiness. Calculate the backlog accumulated before new capacity can help.
Your AI Model Is Fast. Why Are Users Still Waiting?
Trace a slow AI response from client to queue, prefill, decode, and delivery. Learn to investigate a traffic spike before choosing an intervention.
This collection grows section by section. Concepts describe the intended coverage; related reading may introduce only part of a section.
Start Here
Follow the numbered sections in order, or choose the subject you need. Published articles are linked where they support the section.
Python for AI
APIs
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
FastAPI
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Data pipelines
Embeddings infrastructure
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Vector databases
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Knowledge graphs
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Model serving
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
LLM gateways
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Caching
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Queues
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Distributed systems
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
GPU inference
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Docker
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Kubernetes
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Cloud AI
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Reliability
Scalability
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Security
Latency optimization
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.
Cost optimization
Related reading
No published reading is assigned to this section yet. Its place in the learning sequence is reserved as the collection grows.