AI Systems Research Intern – Testing LLM-based Applications

Cybersecurity Group

Deadline for receipt of applications: August 30, 2025 23:59 AoE (31 August 2025, 13:59h Europe/Madrid Time)

Position in evaluating and stress-testing GPT-based applications

Join our research team as an intern focused on evaluating and stress-testing GPT-based applications. You’ll explore novel methodologies for systematic testing of Large Language Model (LLM) behavior, uncovering privacy issues, failures, and unexpected behaviors.

This internship blends cutting-edge AI research with practical experimentation, offering the opportunity to contribute to safer, more reliable AI systems. Ideal candidates have a strong interest in LLMs, software testing, or adversarial analysis.

Duration

6 months, with the possibility of extending the internship.