Build agentic AI security capabilities at American Express, using experimentation, software engineering, and cybersecurity research in a 16-week internship.

This Master’s-level internship focuses on turning research questions into code, experiments, evaluation results, and reusable capabilities. You may work with AI agents, tool calling, orchestration frameworks, retrieval patterns, and automated workflows. The team applies responsible AI, privacy, security, governance, and compliance practices.

Key Responsibilities:

- Translate technical literature into testable research questions
- Build and test AI agents and orchestration workflows
- Conduct security testing and adversarial evaluations
- Assess effectiveness, reliability, limitations, and enterprise applications




- Participate in Agile practices and code reviews

Requirements:

- Master’s enrollment in computer science or related technical field
- Graduation aligned with the 2027 internship eligibility window
- Programming experience with Python and additional modern languages
- Knowledge of AI, cybersecurity, and software engineering concepts
- Robust analytical, written, verbal, and collaborative communication

Bring graduate research, coding, experimentation, and responsible AI knowledge to agentic security engineering at American Express.

#J-18808-Ljbffr

📌 Agentic AI Security Engineering Intern (Toronto)
🏢 American Express
📍 Toronto