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
Customer requirements
Turn vague customer requests into clear requirements, with a reviewer
What you'll learn
Scope boundary
Discovery questions
Technical tradeoff
Demo flow
Practice
Plan a Demo and the Recovery for the Thing That Breaks15 min
Explain a Technical Tradeoff to a Non-Engineer Customer20 min
Chapter 6
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
Chapter 6
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 8
Programming languages
Build small programs in one language, handling input and errors
What you'll learn
Types and values
Control flow
Error handling
Asynchronous work
Practice
Trace a Function and Predict Its Output10 min
Chapter 8
Debugging
Use error messages to find bugs and explain your fixes
What you'll learn
Hypothesis before keyboard
Reliable reproduction
Root cause, not symptom
Narrow it down
Reading a stack trace
Practice
Find the Bug Using an Error Message10 min
9 more in the plan
CommunicationRewrite an update for two different readers, cutting extra linesCh 2
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 2
What you'll learn
Early team friction
Clear ownership
Challenge ideas, not people
Lead or follow
Adapting to changeTry a new tool and describe how you handled changeCh 4
What you'll learn
Change vs your response
The messy in-between
Not there yet
Real change vs a feeling
Problem solvingTest each possible cause of a problem instead of guessingCh 4
What you'll learn
Problem vs symptom
Clean problem splits
Root cause
Deciding under uncertainty
Practice
Separate the Problem from the Symptom10 min
Critical thinkingSpot a weak assumption and ask where numbers come fromCh 4
What you'll learn
The hidden assumption
Argue the other side
The base rate
Fact vs inference
Wanting it to be true
Practice
Spot the Weak Link in an Argument10 min
AI retrievalBuild a system that answers from documents and shows sourcesCh 6
What you'll learn
Text embeddings
Chunk size overlap
Retrieval and prompt
Source grounding
Practice
Build a Mini RAG Pipeline with a Free Embedding API30 min
AI evaluationCollect examples for an AI feature and grade its answersCh 7
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
Design an LLM-as-Judge Eval and Critique Its Blind Spots40 min
Reading codeExplain unfamiliar code and predict what a function outputsCh 8
What you'll learn
Feature entry point
Call chain
Reference search
Code reading notes
Practice
Read 100 lines of unfamiliar code30 min
APIsCheck requests and replies between programs, and design clear onesCh 9
What you'll learn
API resource
HTTP status codes
API contract
Idempotent request
API style choice
Practice
Design REST endpoints for a notes app20 min
Your plan
Chapter by chapter.
13 chapters, in this order. Chapter 1 is free.
1~2 wks
See the work of a Forward-deployed AI engineer
StartFree
2~2 wks
Scope and deliver work with the customer
Skills
3~2 wks
Write up a system you built
Project
4~2 wks
Think problems through when plans change
Skills
51–2 wks
Talk to two working forward-deployed engineers
People
6~2 wks
Build prompts and retrieval that work reliably
Skills
7~2 wks
Measure how good AI answers are
Skills
8~2 wks
Read unfamiliar code and fix its bugs
Skills
9~2 wks
Connect software through APIs
Skills
10~2 wks
Capstone: build a working AI feature
Project
111–2 wks
Answer the questions interviewers ask
Interview
121–2 wks
Decide how you will get in
Decide
13on your timeline
Send your first applications
Apply
The job
What a Forward-deployed AI Engineer does
Embeds with a customer to scope their problem, prototype fast, and build an AI feature directly into their software. Blends strong coding with clear, friendly talk so the customer trusts the result.
The work
Meet a customer to understand their problem and what success looks like
Prototype an AI feature quickly to show what is possible
Build the feature into the customer's own codebase and tools
Connect a large language model (the AI behind chat tools) to real data
Test the feature with the customer and fix what breaks
Iterate on-site as the customer uses it and gives feedback
Hand off clean code and notes so the customer's team can keep it running
A typical day
Join a call with the customer to clarify the problem and goals
Read the customer's codebase to learn how it fits together
Prototype a feature with an AI model, then demo it live
Debug a broken integration using logs and the customer's data
Gather feedback on-site and reshape the plan for tomorrow
Write a short update and a clear handoff for the customer's team
Tools
Languages: Python, TypeScript, JavaScriptAI models and APIs: OpenAI, Anthropic, open-source modelsAI app frameworks: LangChain, LlamaIndex (tools that wire models into apps)Vector databases: Pinecone, pgvector (stores that find similar text)Version control: Git, GitHubCloud platforms: AWS, Azure, Google CloudContainers: DockerNotebooks and demos: Jupyter, Streamlit
Ways in
There is more than one route.
Ways to study
Bachelor degree in computer science, software engineering, or related field
Coding bootcamp focused on software development or applied AI
Diploma or certificate in programming with strong project work
Self-taught path with online AI courses plus a deployed portfolio
How people get their first job
Build 2 to 4 small AI apps that solve a real problem, with clear README files
Apply for engineering internships at AI-native startups
Start as a software engineer and take on customer-facing project work
Contribute to open-source AI tooling to learn how models plug into apps
Join a hackathon and ship a working AI demo in a weekend
How long does it take to become a forward-deployed ai engineer with Welica?
The plan is 13 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, coding bootcamp focused on software development or applied AI, diploma or certificate in programming with strong project work, or self-taught path with online AI courses plus a deployed portfolio.
What is free?
Chapter 1, See the work of a Forward-deployed AI engineer, is free for good. Premium unlocks the rest of the plan.