Loading
Professional Certificate
Generative AI Engineering
Build, evaluate and ship applications on large language models.
- Length
- 6 or 12 months
- Level
- Intermediate
- Weekly
- 8 to 12 hours
- Format
- Live cohort, Hybrid
- Modules
- 8 to 13
- Next intake
- To be announced
What you'll learn
A build-first program for software and data professionals who want to put language models into real products. You learn how models produce text, how to ground them in your own data, how to measure whether they are any good, and how to run them within a budget. Every module ends in working code you keep.
By the end, you will be able to
- Explain tokenization, attention and sampling well enough to debug model behaviour
- Design prompts that return validated, structured output
- Build retrieval-augmented generation pipelines over private documents
- Write evaluation suites that catch regressions before users do
- Add tool use to applications with permission and failure handling
- Deploy an LLM service with tracing, caching and cost controls
Curriculum
Switch between the 6- and 12-month options to see how the program expands. Every module includes a hands-on lab.
8 modules, 24 weeks, about 192 to 288 study hours
Core modulesCapstone
Topics
- Async I/O and rate limits
- Pydantic models for structured data
- Retries, timeouts and idempotency
- Secrets and configuration
Lab
Build a resilient client wrapper with backoff and logging
Estimated effort
24 to 36 hours over 3 weeks
Skills you'll build
- Prompt designAdvanced
- Retrieval-augmented generationAdvanced
- LLM evaluationAdvanced
- Tool useProficient
- Fine-tuningProficient
- LLMOpsProficient
Tools and technologies
- Python
- Pydantic
- FastAPI
- OpenAI API
- Anthropic API
- Hugging Face
- LangChain
- pgvector
- Docker
- GitHub Actions
Product names are trademarks of their owners, listed only to describe what we teach. No endorsement is implied.
Portfolio projects
Representative projects from the curriculum. Your capstone is scoped with a mentor around a problem you choose.
Cited policy assistant
Answer employee questions from a 300-page handbook, with citations and refusal when unsure.
RAG, pgvector, FastAPI
Ticket triage service
Classify and route inbound support messages into validated JSON with an eval suite guarding quality.
Structured output, Evals, CI
12-month option
Invoice extraction pipeline
Pull line items from scanned invoices with a vision-language model and confidence-based human review.
Multimodal, Fine-tuning, Queues
How it's delivered
- Live cohort
- Scheduled live classes each week with your cohort, recorded for different time zones, plus self-paced lessons and labs.
- Hybrid
- Self-paced lessons with fortnightly live workshops and mentor sessions.
Instructors
Instructor and mentor profiles for this program are published once each person's background has been verified. We don't show placeholder faces or borrowed credentials.
Admissions
- 1Submit an online application
- 2Readiness review by admissions
- 3Decision by email
- 4Confirm your place and start onboarding
Tuition
- 6-month optionPublished before intake
- 12-month optionPublished before intake
Payment options vary by country and are shown at checkout.
Tuition and payment optionsCertificate
Complete every required module, pass the assessments and the capstone review to earn the Professional Certificate.
Each certificate has a unique ID and QR code that anyone can check on our verification page.
This is a professional credential issued by Zyvora Academy, not an academic degree.
Where it can lead
Roles this program builds toward. Outcomes depend on your background, effort and local job market; we don't guarantee employment.
AI Engineer
Builds products and internal tools on top of language and multimodal models.
Role details
Program questions
Syllabus
Get the full syllabus
We'll email the detailed syllabus, and the fee sheet as soon as tuition for the next intake is published.
Advisor
Speak to an advisor
Ask about fit, prerequisites or which length suits you. An advisor replies by email to arrange a call.
