Each skill is a few short lessons, then practice. You rate yourself at the start and again at the end.
Core to the job
Chapter 2
AI language models
Measure the size of AI requests and compare randomness settings
What you'll learn
Tokens and context
Sampling variation
Model trade-offs
Embeddings for search
Practice
Count Tokens and Predict Context Limits15 min
Choose and Justify a Model Stack for Three Real Scenarios25 min
Chapter 2
Prompt engineering
Write prompts that use examples and ask for machine-readable answers
What you'll learn
System and user prompts
Format constraints
Few-shot examples
Prompt versions
Practice
Fix a Flaky Prompt by Adding a Format Constraint15 min
Chapter 4
AI retrieval
Build a system that answers from documents and shows sources
What you'll learn
Text embeddings
Chunk size overlap
Retrieval and prompt
Source grounding
Practice
Spot the Chunking Problem in a RAG Answer15 min
Chapter 6
AI evaluation
Collect examples for an AI feature and grade its answers
What you'll learn
Golden dataset
Scoring rubric
Judge model limits
Quality threshold
Production sampling
A real drop or noise
Scoring an agent run
Practice
Grade a Chatbot's Answers Against an Answer Key20 min
Chapter 6
AI feature safety
Spot tricks that make an AI ignore its rules
What you'll learn
Prompt injection
AI attack surface
Guardrail layers
Guardrail trade-off
AI threat model
Agent action risk
Practice
Spot the Guardrail Gap in These Test Prompts15 min
Chapter 7
APIs
Check requests and replies between programs, and design clear ones
What you'll learn
API resource
HTTP status codes
API contract
Idempotent request
API style choice
Practice
Design a Bookmark-Saving API20 min
8 more in the plan
Programming languagesBuild small programs in one language, handling input and errorsCh 7
What you'll learn
Types and values
Control flow
Error handling
Asynchronous work
Cloud platformsRead a cloud bill and find which services cost mostCh 7
What you'll learn
Core cloud services
Identity and permissions
Service tradeoffs
Cloud cost drivers
Well-Architected review
Practice
Read a Cloud Bill and Spot What's Costing Money15 min
System design basicsSketch a simple web app and explain how data flowsCh 8
What you'll learn
System boundary
Synchronous and async
Cache trade-off
Failure mode
Browser and server
Vertical slice
Practice
Choose Between Polling and Push Notifications20 min
Secure codingFind risks in a login process and remove exposed passwordsCh 8
What you'll learn
Trust boundaries
Access control
Secret handling
Dependency risk
Practice
Spot Security Risks in a Login Flow15 min
Problem solvingTest each possible cause of a problem instead of guessingCh 9
What you'll learn
Problem vs symptom
Clean problem splits
Root cause
Deciding under uncertainty
Practice
Separate the Problem from the Symptom10 min
CommunicationRewrite an update for two different readers, cutting extra linesCh 9
What you'll learn
Lead with the point
Match detail to the reader
Said versus heard
Specific feedback
Practice
Write a Status Update for a Non-Tech Manager10 min
Working with othersContribute to group work, ask for help and credit teammatesCh 9
What you'll learn
Early team friction
Clear ownership
Challenge ideas, not people
Lead or follow
Practice
Navigate a Disagreement Without Damaging the Relationship20 min
Adapting to changeTry a new tool and describe how you handled changeCh 10
What you'll learn
Change vs your response
The messy in-between
Not there yet
Real change vs a feeling
Your plan
Chapter by chapter.
14 chapters, in this order. Chapter 1 is free.
1~2 wks
See the work of an AI platform engineer
StartFree
2~2 wks
Write prompts that give reliable answers
Skills
3~2 wks
Write up a system you built
Project
4~2 wks
Feed models the right facts
Skills
51–2 wks
Talk to two working platform engineers
People
6~2 wks
Measure AI feature quality and safety
Skills
7~2 wks
Build and run APIs in the cloud
Skills
8~2 wks
Design a system and secure its code
Skills
9~2 wks
Explain problems and solve them together
Skills
10~2 wks
Adapt well when work changes
Skills
11~2 wks
Capstone: build a working AI feature
Project
121–2 wks
Answer the questions interviewers ask
Interview
131–2 wks
Decide how you will get in
Decide
14on your timeline
Send your first applications
Apply
The job
What a AI Platform Engineer does
Builds the internal platform that lets a whole company use artificial intelligence (AI) safely and fast. It produces shared tools: a gateway to large language models (LLMs), evaluation systems, and search pipelines. Other engineers then ship AI features without rebuilding the basics each time.
The work
Build a gateway that routes requests to many large language models (LLMs)
Create tools to store, version, and test prompts across teams
Set up evaluation pipelines that score model output for quality
Run a vector database (one that finds text with similar meaning) for fast search
Build retrieval-augmented generation (RAG) pipelines that feed models trusted data
Add guardrails that block unsafe, leaking, or wrong AI responses
Track cost, speed, and errors so teams can debug AI features
Document the platform and support engineers who build on it
A typical day
Check dashboards for model errors, cost spikes, and slow requests
Plan platform work in a short sync, then share changes with the engineering team
Build or review a feature for the LLM gateway or evaluation tools
Help a product team debug a flaky retrieval-augmented generation (RAG) pipeline
Test new prompt versions against a saved set of scored examples
Tune guardrails after a model returns an unsafe or wrong answer
Tools
Languages: Python, TypeScript, GoModel gateways: LiteLLM, OpenRouter, cloud model APIsOrchestration: LangChain, LlamaIndexVector databases: Pinecone, Weaviate, pgvectorEvaluation: LangSmith, Ragas, custom test setsPrompt tools: PromptLayer, Git for versioningInfra and cloud: Docker, Kubernetes, AWS, Azure, Google CloudObservability: Grafana, Prometheus, tracing
Ways in
There is more than one route.
Ways to study
Bachelor degree in computer science, software engineering, or related field
Strong software engineering background plus self-study in machine learning
Online courses in large language models, retrieval, and platform engineering
Several years of backend or platform work before moving into AI tooling
Master degree in machine learning or data engineering for deeper theory
How people get their first job
Build a backend or platform engineering base first, then add AI projects
Ship a small retrieval-augmented generation (RAG) app with tests and clear docs
Contribute to open-source large language model (LLM) tools and pipelines
Move from backend or DevOps work into a team that builds AI tooling
Run an evaluation harness for a model and publish the results as a portfolio piece
How long does it take to become a ai platform engineer with Welica?
The plan is 14 chapters, 5–6 months at 15 to 30 minutes a day. You can go faster or slower; the plan moves with you.
Do I need a degree?
Not always. Common routes are bachelor degree in computer science, software engineering, or related field, strong software engineering background plus self-study in machine learning, online courses in large language models, retrieval, and platform engineering, several years of backend or platform work before moving into AI tooling, or master degree in machine learning or data engineering for deeper theory.
What is free?
Chapter 1, See the work of an AI platform engineer, is free for good. Premium unlocks the rest of the plan.