Loading…
Build AI features a business can trust
The route to building with generative AI professionally, not just using chatbots. Learn the Python and machine learning foundations, then build LLM features properly: prompts as specifications, validated outputs, retrieval with citations, evaluation against human labels, and the privacy, safety and cost controls that decide whether a feature can launch.
What you'll be able to do
CloudTech AI Engineer
Complete every required course to earn the track badge, free, with a credential ID anyone can verify.
Start with Python for Data AnalyticsThe Python and machine learning every AI engineer relies on.
pandas for loading, cleaning and exploring the data AI features run on.
About 9 hours
Sampling and uncertainty, for reading evaluation results honestly.
About 8 hours
Train and test splits, baselines, recall and cost-based decisions.
About 9 hours
Build LLM features properly.
Prompts, validation, retrieval, evaluation, safety and cost, on a mobile wallet's support assistant.
About 7 hours
Feature Engineering and Model Evaluation
Calibration, drift and monitoring: the habits that keep models working after launch.
About 7 hours
Go further into AI systems.
Scoped tools, rules in code, guarded loops, approvals and injection defences, on a support agent's recorded runs.
About 7 hours
LLM Evaluation and Safety in Production
Release gates, red-teaming, fair guardrails, alerts and incident response for a live assistant.
About 7 hours
Turn your skills into applications that get interviews.
An ATS-friendly CV and a LinkedIn profile recruiters can find.
1 hr 30 min
One link that shows your notebooks and evaluation reports.
1 hr 25 min
Courses marked "In preparation" join the track when they're ready. If you've already earned the track badge by then, you keep it.