AI Safety and Alignment
Technical and governance approaches to making AI go well
About this program
Six months on the rapidly maturing field of AI safety. Covers interpretability, evaluations, red-teaming, scalable oversight, and the governance side of frontier AI risk. Designed for engineers and policy professionals who want to contribute to safety work in industry, academia, or government.
Student ratings
Excellent — 231 verified Canadian graduates rated this program 4.7/5. Reviews emphasize the applied capstone, instructor responsiveness, and career outcomes.
- 5★172
- 4★52
- 3★5
- 2★1
- 1★1
Who this program is for
- →Practitioners already shipping ai ethics & policy work who want depth
- →Senior engineers, data scientists, and technical leads
- →Canadian residents seeking a verifiable diploma credential
Topics you'll cover
6 modules across 6 months — 24 lessons in total.
Six-month syllabus
Module 1 · Month 1 — Why Safety▾
- L1Risk categories
- L2Scaling laws and capability
- L3Historical incidents
- L4The case for and against
Module 2 · Month 2 — Evaluations▾
- L1Capability evals
- L2Safety evals
- L3Building eval harnesses
- L4Inspect framework
Module 3 · Month 3 — Red-Teaming▾
- L1Threat models
- L2Manual and automated red-teaming
- L3Jailbreaks and defenses
- L4Reporting standards
Module 4 · Month 4 — Interpretability▾
- L1Mechanistic interpretability
- L2Sparse autoencoders
- L3Activation patching
- L4Practical lab work
Module 5 · Month 5 — Governance▾
- L1Frontier AI policy
- L2Voluntary commitments
- L3UK AISI, US AISI, Canadian context
- L4Compute governance
Module 6 · Month 6 — Capstone▾
- L1Original safety project
- L2Write-up to academic standards
- L3Peer review
- L4Optional submission
What you'll be able to do
- ●Run rigorous evaluations of frontier models
- ●Conduct structured red-team exercises
- ●Apply interpretability techniques
- ●Contribute to safety research
- ●Advise on frontier AI governance
Career paths after graduation
Frequently asked questions
How much does the AI Safety and Alignment cost?▾
Tuition is $699 CAD. You can pay in full at checkout or choose an interest-free monthly plan. A 30-day refund window applies from your start date.
How long is the AI Safety and Alignment program?▾
6 months, cohort-based and fully online. Expect roughly 13 hours per week including live Thursday sessions at 7pm ET.
What are the prerequisites?▾
Strong technical background or policy expertise
Is the diploma recognized in Canada?▾
Yes. Graduates receive the Altaris AI Academy Diploma in AI Ethics & Policy — a verifiable credential with a unique certificate number you can publish on LinkedIn and that any employer can verify at smart-ai-future.lovable.app/verify.
What is the refund policy?▾
Full refund within 30 days of your cohort start date, no questions asked. After day 30, prorated refunds are available per our Refund Policy.
Who teaches the program?▾
Working Canadian AI practitioners — not academics. Each cohort has a lead instructor plus a 1:1 mentor pairing for the duration of the program.
Students also enrolled in
More AI Ethics & Policy programs from Altaris.