Berlin (Prenzlauer Berg) or live online

Build and Evaluate LLM Applications

AI engineering is building products that use LLMs, like chatbots, search over your company's documents or agents that do tasks for users. A 3-month (13-week) full-time course for developers who already write code. 15 seats, taught live by me, Alexey Grigorev.

This program is based on LLM Zoomcamp, AI Engineering Buildcamp, and my experience building AI products and putting them in production.

Join the waitlist to hear when the next cohort opens.

I'm Alexey Grigorev. I have taught more than 100,000 students in DataTalks.Club courses.

15 seats, 1 instructor

COHORT: Waitlist open
FORMAT: Full-time, live, 3 months (13 weeks)
WHERE: Berlin (Prenzlauer Berg) or live online
LANGUAGE: English
SEATS: 15
TUITION: Bildungsgutschein (approval pending) or €9,000 to €10,000 self-pay

By the end you can build an AI application, and show where it works and where it fails.

01Build an assistant in Python on an LLM API.
02Use retrieval-augmented generation (RAG) and document processing over company data.
03Give the assistant tools, function calling and MCP connections to look things up or call an API.
04Define what it can do on its own and when it needs human approval.
05Evaluate answers and tool use on realistic tasks, compare prompts and models, and catch regressions.
06Deploy the application to the cloud and trace its model and tool calls.
07Track quality, latency and cost, and handle failures safely with guardrails.

The Final Project

You build and deploy an AI assistant for a concrete company use case, for example one that answers questions from messy internal documents with sources and carries out actions after human approval. You show where it works, where it fails, and how you measured that.

I Teach Every Session and Review Every Project

I'm Alexey Grigorev. I have taught more than 100,000 students in DataTalks.Club courses. I founded DataTalks.Club and created its free Zoomcamps on data engineering, machine learning, MLOps, LLMs and AI dev tools. I also wrote Machine Learning Bookcamp and teach paid cohort courses on Maven.

This cohort has 15 seats. I teach every day myself and look at every participant's project every week. There are no teaching assistants and no pre-recorded lectures.

This Is for You If

You program today, ideally in Python, and can use APIs and work in a repository.
You can study full-time, Monday to Friday, for the whole program.
You can follow technical teaching and work with others in English.
You want your next job to be in software or AI engineering, including if you are between jobs right now.

This Is Not for You If

You have never programmed. Start with the free Zoomcamps and come back.
You need an evenings-only course.
You want a certificate without building anything.

Sixteen Modules, One Project That Grows Every Week

This is the draft syllabus. I use the waitlist's survey answers to shape the final version.

Weeks 1 to 4Retrieval

01Agentic engineering basics and a Python service on an LLM API.You produce: a working coding-agent setup (day 1) and a small API that returns validated, structured answers.
02Retrieval, document processing and indexing.You produce: a one-command ingestion pipeline and a knowledge assistant with sources.
03Vector and hybrid search.You produce: three retrieval variants, with examples of where each fails.
04Evaluating retrieval.You produce: a retrieval evaluation and a justified configuration.

Weeks 5 to 7Agents

05Agentic engineering workflow, tools and the agent loop.You produce: the full agent workflow on your project repo (spec to tasks, tests, diff review, CI) and an assistant that calls an API through a tool.
06Agent frameworks, MCP and context.You produce: the assistant rebuilt on a framework, with one MCP tool.
07Serving and cloud deployment.You produce: a deployed assistant with cited answers and one tool (midterm).
08Agentic workflows and human approval.You produce: a workflow action that waits for approval and handles refusal.

Weeks 8 to 9Quality and production

09Testing LLM applications and CI/CD.You produce: a regression suite running in CI.
10Evaluating answers and agents.You produce: an evaluation report comparing two configurations.
11Tracing, monitoring, cost and latency.You produce: traces, dashboards, and a cost/latency report with a measured improvement.
12Safety: guardrails, injection and compliance.You produce: tested guardrails and a short compliance checklist.

Weeks 10 to 13Capstone and interviews

13Technical interviews and hiring prep (full week, 30 hours).You produce: algorithm coding drills without AI, a timed take-home, a project presentation and first peer mocks.
14Capstone I and interview practice.You produce: your 60-hour capstone assistant core alongside weekly coding drills and squad mock interviews.
15Capstone II and interview practice.You produce: evaluation evidence, improved assistant, mock interviews and project-talk rehearsals.
16Capstone III: deploy, defence and career prep.You produce: the deployed assistant, defence, final 30 hours of interview practice and 3 individual 45-min career consultations plus written CV review.

How Tuition and the Bildungsgutschein Work

I'm applying for AZAV certification so the Agentur für Arbeit can cover tuition with a Bildungsgutschein.

The voucher and the seat are separate decisions. The Agentur decides whether it pays, and I decide who is in the cohort.

If you pay yourself, the full program costs €9,000 to €10,000.

How the Bildungsgutschein works (arbeitsagentur.de)

Why 15 Seats

I teach this cohort myself and review every project. I can do that properly for about 15 people, not for more. If more people qualify than there are seats, there is a waitlist and a later cohort. I won't add seats.

01
Join the waitlist. Leave your name and email on this page. There is no commitment.
02
Apply first. When applications open, the waitlist gets them before anyone else.
03
Short task and a conversation. A small practical exercise and a 20-minute call, so we both know the level fits.
04
Seats are offered in rounds. Everyone who applies gets an answer.

Questions

When does the next cohort start?

There is no active cohort right now. Join the waitlist and I'll write to you when dates open.

What do I get for joining the waitlist?

You get the application before it opens publicly, and updates on dates, format and funding approval. Nothing else, and no obligation.

What do I need to know before I start?

You are comfortable programming, preferably in Python, and you can use the command line, Git and basic Docker. You don't need a machine-learning background, advanced mathematics or a GPU.

Will the Agentur für Arbeit pay for it?

That is the plan. I'm applying for AZAV certification so the Agentur für Arbeit can pay with a Bildungsgutschein. Talk to your adviser early.

What does it cost if I pay myself?

€9,000 to €10,000 for the full program.

Is it online or in Berlin?

Berlin (Prenzlauer Berg) or live online. In person, it is near S+U Schönhauser Allee. Online, you join live from Germany. The survey after you join asks which one you could attend.

What is the schedule?

Full-time: Monday to Friday, 09:00 to 16:00 Berlin time, live, for 3 months (13 weeks). I'm also considering a part-time version. Tell me in the survey if you need one.

Do I have to live in Germany?

The program is built for people in Germany, and a Bildungsgutschein is only available there.

How do you choose who gets a seat?

By the same published criteria for everyone: programming experience that fits the track, availability for the full schedule, English, a concrete goal, and the practical task. Your employment or benefit status is not a criterion.

What happens to my email?

I use it only to write to you about this program and its application. You can ask me to delete it at any time. Details are in the privacy notice.

Join the Waitlist

Leave your name and email and I'll write to you when the next cohort opens.