Skip to content
UltiblobStatus
Back to catalog
Intermediate2 days / 10 to 14 guided hourspublished

AI Engineer Career Path: Intermediate

Build a RAG application with evaluation, observability, and troubleshooting scenarios.

Start labOpen in lab portal

Audience

  • Self-paced technical learners
  • Instructor-led cohorts
  • Enterprise teams preparing staff for hands-on operations

Prerequisites

  • Beginner course or equivalent experience
  • Comfort with command-line or admin consoles

Outcomes

  • Provision an isolated ai engineer career path lab from template metadata.
  • Use snapshots, rollback, validation checks, and teardown safely.
  • Explain how LiteLLM, Ollama, Qdrant, Python fit into an enterprise training environment.
  • Produce evidence that an instructor or admin can review.
Course plan

Modules and labs

Each module maps to provisioned lab work, validation evidence, reset/rollback policy, and instructor visibility.

Module 1

Scenario design

AI Engineer Career Path Intermediate lab 1
Module 2

Multi-system implementation

AI Engineer Career Path Intermediate lab 2
Module 3

Troubleshooting and reporting

AI Engineer Career Path Intermediate capstone
Required templates

Python data science workstation

defined

Ubuntu 24.04 LTS

Vector database/RAG node

defined

Ubuntu 24.04 LTS plus Qdrant or compatible vector DB

Ollama/LiteLLM client node

defined

Ubuntu 24.04 LTS

Validation checks

Notebook reachable

JupyterLab returns a valid login page or authenticated health response.

AI endpoint reachable

The model gateway returns at least one allowed model for the tenant.