International Programme on AI Evaluation: Capabilities & Safety
AI is advancing faster than our ability to evaluate it. We are changing that.
This programme brings together 40 exceptional students and professionals from around the world for a 150-hour hybrid course that blends lectures, hands-on labs, and a capstone project week in Valencia.
Fully funded through Open Philanthropy and certified by ValgrAI, it is the first step toward establishing AI Evaluation & Safety as a formal academic discipline.
Format at a Glance
150 hours hybrid programme. From February to May 2026
90 hours of online lectures, seminars, and activities.
20 hours of hands-on courses to apply evaluation methods to real-world AI systems.
40 hours in-person capstone week in Valencia, Spain. Collaborative project work with academic mentorship, guest keynotes, and practical labs.
Student Experience
Community: Cohort of 40 top international participants, fostering collaboration and peer learning.
Mentorship: Direct guidance from leading researchers in academia, industry, and government.
Credential: 15 ECTS Expert Diploma from ValgrAI.
Scholarship: All students receive full funding, including travel and accommodation support for the in-person week.
Curriculum Highlights
Participants will explore the following modules, each with an evaluation activity designed to provide hands-on experience.
Introduction to AI Evaluation
AI Architectures: Large Language Models and Beyond
Metrics and Experimental Methodology
Benchmarks, Leaderboards, and Competitions
Red-teaming Evaluations
Construct-Based Evaluation
Mechanistic Interpretability
AI Alignment and Control Evaluations
Governance, Policy, and Regulation of AI
Real-world Evaluations: Societal Impacts of AI
The programme culminates in a Capstone Project, where teams design and carry out an original evaluation study under the guidance of expert mentors, to produce publishable-quality work.
What You’ll Gain
By the end of the programme, you will:
Build core expertise in AI evaluation methods, from benchmarks and interpretability to red-teaming, governance, and societal impact.
Apply these skills in practice, evaluating real-world systems and completing a mentored capstone project.
Position yourself for impact in AI Safety Institutes, frontier labs, and policy bodies, or as researchers continuing into PhD and postdoctoral work.
Join a global network of peers and faculty shaping the future of AI evaluation and safety.
How We Are Different
This is not a bootcamp, an online course, nor a focused research program.
This is the first global academic programme focused on AI evaluations.
We offer you a comprehensive overview of the tools, and practical frameworks used to test, interpret, and govern advanced AI systems.
We show you the map, so you can connect the dots across disciplines: learning how technical evaluation, interpretability, governance, and policy interact.
