If you can already write code, you are closer to an AI engineering role than most job descriptions make it look. You do not need a research background or a PhD. You need to learn how to build, harden, and ship systems that use large language models — and how to talk about them clearly.
This post is the short version of the roadmap. It is written for developers, not researchers.
What an AI engineer actually does
An AI engineer builds software products that use models as components. Day to day that means:
- Designing retrieval and context pipelines (RAG) so models answer from your data.
- Building agents that use tools, memory, and control flow safely.
- Adding evals, tracing, guardrails, cost controls, and latency budgets.
- Exposing clean APIs and deploying to real environments.
Notice what is missing: training foundation models from scratch. That is research. Most hiring is for people who can apply models well.
The skills that matter
You do not need everything at once. Learn in this order:
- LLM fundamentals — tokens, context windows, embeddings, prompting.
- RAG — chunking, vector search, reranking, grounding, citations.
- Agents — tool use, function calling, planning, memory, human-in-the-loop.
- Production — evaluation, observability, retries, cost and latency, safety.
- Delivery — APIs, Docker, secrets, deployment, basic cloud.
Projects that get you hired
Interviewers trust projects more than certificates. Build three:
| Project | What it proves |
|---|---|
| A RAG service over real docs | You can ground models in data and evaluate quality |
| A tool-using agent | You understand control flow, tools, and safety |
| A production-hardened app | You can deploy, observe, and control cost |
Each project should have a clean README, an architecture diagram, and a short
note on trade-offs. That is what makes them legible in interviews.
A 90-day plan around a full-time job
With one to two hours on weekdays and a few hours on weekends:
- Weeks 1–3: fundamentals + a minimal RAG service.
- Weeks 4–6: harden it — evals, tracing, cost, a real deployment.
- Weeks 7–9: build a tool-using agent.
- Weeks 10–12: interview prep — system design, project talking points, mock questions.
Where to go next
Grab the AI Engineer Roadmap for the expanded version with project specs and a study schedule, then start with the blog. Build in public, put every project on GitHub, and explain your decisions. That combination — real projects plus clear communication — is what turns a developer into an AI engineer.