What inspired you to join the alignAI project?

I have always been interested in building safer and more trustworthy AI systems. The alignAI project offered a unique opportunity to work on real-world alignment challenges with an interdisciplinary team.

What is the focus of your research within alignAI?

My research explores how to improve the robustness of large language models (LLMs), especially in scenarios where safety and alignment may be challenged by different user groups, adversarial prompts or downstream adaptations.

What excites you most about working at the intersection of AI and robustness?

I’m excited by the challenge of making AI models more trustworthy and safer, especially when they are deployed in dynamic environments or interact with humans.

How do you see interdisciplinary collaboration shaping the future of AI, whether in your project or further?

I believe interdisciplinary collaboration is essential for developing AI systems that are not only technically robust but also socially responsible. By combining insights from computer science, social sciences and humanities, we can align AI with human values and ensure models are explainable, fair and trustworthy across real-world contexts.

If you had to explain your research to a friend outside academia, how would you describe it?

I’m working on making AI models trustworthy and robust. My goal is to ensure they stay safe and work properly, even in unpredictable real-world situations, while being aligned with human values to avoid unintended consequences.

Where can people follow your work?

You can find my works on Google Scholar and LinkedIn.