OfferReady
← Keep up with AI

12-week AI roadmap

What to study each week to become an AI engineer or a forward deployed engineer, with the interview questions for each week.

12 weeks · about 1 hour a day

Week 1: How LLMs work

Each week: learn it, build one small thing, then practice the questions interviewers ask about it. What you build becomes your interview stories.

Foundations

Weeks 1 to 4
  1. Week 1How LLMs workThis week
    Learn
    • Tokens, context windows and why they decide cost
    • Embeddings in one sentence
    • Temperature and why answers vary
    • Pricing: input, output and cached tokens
    Build

    Call an LLM API from a script. Print the tokens used and the cost of each call.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

  2. Week 2Prompting and structured output
    Learn
    • System prompts, examples (few-shot) and clear instructions
    • Getting reliable JSON back
    • Why small prompt changes break things
    Read in our study library
    Build

    Turn messy job posts into clean JSON (title, skills, years). Test it on 10 real posts.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

  3. Week 3Embeddings and search
    Learn
    • Chunking text and why chunk size matters
    • Similarity search and vector databases
    • Hybrid search: keywords plus embeddings
    Build

    Semantic search over your own notes or docs. Compare it with plain keyword search.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

  4. Week 4RAG end to end
    Learn
    • Retrieve, add to the prompt, answer with citations
    • Why RAG answers go wrong (bad retrieval, stale data)
    • Context engineering: what to include and what to leave out
    Build

    A Q&A bot over a set of documents that cites the passage it used.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

Build like a pro

Weeks 5 to 8
  1. Week 5Evals: proving it works
    Learn
    • Golden test sets
    • LLM-as-judge and its limits
    • Catching regressions before users do
    Build

    Write 30 test questions for your week 4 bot, score it, change one thing, score it again.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

  2. Week 6Agents and tool use
    Learn
    • Tool (function) calling
    • Workflows vs agents, and when an agent is the wrong choice
    • MCP: connecting models to tools and data
    • Guardrails and human approval
    Build

    An agent with two tools (for example search and a calculator) that asks before any action.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

  3. Week 7Frameworks: LangChain and LangGraph
    Learn
    • Graphs, state and memory
    • Human-in-the-loop steps
    • When to skip a framework and write plain code
    Build

    Rebuild your week 6 agent as a LangGraph graph with an approval step.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

  4. Week 8Production: cost, speed, safety
    Learn
    • Prompt caching and batching
    • Latency budgets and streaming
    • Logging and tracing every call
    • Prompt injection and personal data
    Build

    Add cost per request, caching and a log of every call to your project. Cut its cost and write down by how much.

    Example to run and change

    Edit the code and run it again. It runs in your browser; the first run downloads Python (about 10 MB).

Get hired

Weeks 9 to 12 · AI engineer track
  1. Week 9Fine-tuning vs RAG vs prompting
    Learn
    • What fine-tuning changes and what it can’t
    • Smaller, cheaper models for narrow jobs
    • Choosing with data, not taste
    Build

    Try one task three ways (prompt only, RAG, a smaller model). Compare quality, cost and speed in a table.

  2. Week 10System design for AI
    Learn
    • Design an AI support assistant end to end
    • Data flow, evals, fallbacks and monitoring
    • Trade-offs you must be able to defend
    Build

    Draw the design of your project: components, data, evals, costs, what fails and what happens then.

  3. Week 11Portfolio and your stories
    Learn
    • A README that shows the problem, the result and the numbers
    • Turning projects into STAR stories
    Build

    Publish one project with a short demo, your eval results and your cost numbers.

  4. Week 12Interview sprint
    Learn
    • Mock interviews, out loud
    • Fix your weakest area
    • Questions to ask them
    Build

    Two voice mocks this week. Retry every answer that scored under 70.

Free courses worth your time

All free. Pair them with the week you’re on; the study library chapters above cover the interview angle.

Start here
LLMs and generative AI
Agents and production
Go deeper

0 of 12 weeks done. Ticks are saved on this device. Behind? Keep going at your own pace; finishing beats speed. Courses and docs are outside sources, reviewed October 2026. No course or roadmap guarantees a job or a salary. Practice only, never during a live interview.

Send feedback

What worked, what didn’t, what’s missing. Short is fine.

How useful is OfferReady so far?

Please don’t paste passwords or private details. We save the page you’re on, not your answers.