Models, APIs and structured prompting
Model choice, instructions, examples, context, versioning and quality-cost-latency trade-offs.
From LLM prototypes to reliable applications
LLM Engineering
Build reliable LLM applications connected to your data.
Build a reliable LLM application with structured prompting, typed outputs, vector search, RAG, evaluations and quality-cost-latency optimization.
Artificial IntelligenceLIVE COURSE
20 h
of group sessions
Intermediate
level
FR + EN
Discord
01 — OUTCOME
What you’ll be able to do
Select a model and version reproducible prompts
Produce typed outputs and integrate tool calls
Build and measure relevant vector search
Build and evaluate a RAG architecture
Deploy an observable and optimized LLM service
02 — CURRICULUM
A clear, progressive learning path
Detailed content may evolve to stay aligned with current tools and practices.
Structured outputs and tool calling
JSON Schema, validation, refusals, errors and application service integration.
Embeddings and vector search
Chunking, metadata, indexing, semantic search, filters and relevance measurement.
End-to-end RAG
Ingestion, retrieval, grounded answers, citations, updates and access control.
Evaluation, adaptation and safety
Test sets, graders, regressions, prompting/RAG/fine-tuning decisions and injection defense.
Optimization and production
Observability, caching, streaming, tokens, routing, rate limits, cost, latency and monitoring.
Project & deliverables
- A structured extraction app connected to an LLM API
- A RAG application with sources, citations and an evaluation dataset
- A deployable service with a quality-cost-latency report
Prerequisites
Intermediate Python or TypeScript, HTTP/JSON APIs and Git. Advanced model-training knowledge is not required.
03 — FORMAT
Live guidance, practice and feedback.
Group sessions
Demonstrations, exercises, reviews and Q&A over video calls.
Practical deliverables
Guided outputs that apply the skills to realistic scenarios.
Discord
A private space for announcements, questions and peer support.
04 — ENROLMENT
One clear plan, delivered live with the group.
One-time payment. Software subscriptions, API credits and cloud services are not included.
Voluntary satisfaction guarantee
Join with confidence: request a full refund before the second group session begins.
Cohort
€849 TTC
The complete course, delivered live with your group.
- 20 h of live group training
- Exercises and guided deliverables
- Supporting resources
- Private Discord
- Certificate of completion
Full refund on request before the 2nd group session.
The schedule is sent by email.
05 — FAQ
Before joining the cohort
How is the course delivered?
The course includes 20 hours of live group sessions, exercises, practical deliverables and supporting resources.
When will I receive the schedule?
The cohort schedule is sent by email.
What does the Cohort plan include?
The plan includes 20 hours of live group training, guided exercises and deliverables, supporting resources, access to the private Discord and a certificate of completion.
What certificate will I receive?
At the end of the course, you will receive a Genial AI Academy certificate of completion confirming that you completed the training. It is separate from a professional certification.
Is the course recorded?
The initial format is based on live sessions. Access to a complete recorded course library is not promised.
Can I pay by card or PayPal?
Yes. One-time payment is available by card through Stripe or with PayPal.
How does the guarantee work?
You may request a full refund before the second group session begins, without giving a reason.
Ready to begin?
A practical path, live interaction and a community to grow with.
View the plan