Internship: AI Cybersecurity

Internship: AI Cybersecurity & Trust Engineering

Location:
Casablanca, Morocco Company: Cognitive Machines Technologies (CMX) Period: February to June 2027 Duration: 4 months | Final-Year Internship (PFE) At CMX, we're interested in a question that is becoming increasingly important: How do we make intelligent systems secure and trustworthy, especially when they can make decisions and take actions on their own? We're looking for engineering students who enjoy investigating difficult problems, experimenting with new approaches, and building systems that can be tested and verified. Research Areas
• LLM security, prompt injection, jailbreaks, and adversarial attacks.
• Agentic AI security, tool permissions, identity, and multi-agent trust.
• AI governance, policy enforcement, and guardrails.
• Privacy engineering, PII detection, anonymization, and data protection.
• Zero Trust, API security, OAuth 2.0, OIDC, RBAC, and ABAC.
• Threat detection, security observability, and formal verification. Your Research MissionUsing our CMX Cognitive Framework, you'll investigate existing approaches, formulate hypotheses, design a security architecture, develop a working prototype, and evaluate it through experiments. We don't expect you to know every technology. What matters is your ability to understand a problem, question assumptions, and learn through engineering. Three Questions Before You ApplyWe'd like to understand how you think. Please answer these questions in your own words.
• An AI agent can read internal company documents and send emails. One document contains a malicious instruction hidden inside its content. How could this compromise the system? How would you prevent it?
• A security system detects 99% of attacks, yet employees complain that it's almost impossible to use. How could both statements be true? What would you investigate?
• Two AI agents collaborate. One can access confidential information, while the other is only allowed to access public information. How would you prevent confidential information from passing indirectly between them?

How to Apply
Please send the following to contacts@cmxarchi.com:
• Your CV.
• A Word document (.docx), maximum two pages, containing your answers to all three questions.
• Your GitHub profile, portfolio, or relevant projects, if available. You may use AI tools and external resources, but you must explain your own reasoning and disclose the tools or sources used. Important: Applications without answers to all three questions in the requested Word format will not proceed to the next selection stage. Shortlisted candidates will be invited to the CMX Talent Acquisition Day in early January 2027 for an in-person assessment and interview. At CMX, we value people who are curious enough to ask difficult questions and disciplined enough to test their answers.
• #CMX #Internship2027 #PFE #Cybersecurity #AISecurity #LLMSecurity #Casablanca