Postdoctoral Research position on Adversarial Machine Learning
Pubblicato il 04-10-2026 - Altro in Italia
Postdoctoral Research position on Adversarial Machine Learning & Formal Verification AI4I is looking for a creative and highly motivated postdoc or research scientist to join our founding team and help build the next generation of secure agentic AI systems through cutting‐edge research in adversarial machine learning and formal verification.
The Role As a research scientist, you will contribute to frontier AI research that addresses emerging security threats in AI products, particularly as autonomous agents become more sophisticated and widely deployed. Working alongside a dedicated team of security researchers, you will have the chance to shape the future of AI security by developing novel defense mechanisms, verification methods, and security frameworks that can withstand adversarial attacks.
Key Responsibilities Conduct foundational research in adversarial machine learning, exploring novel attack vectors and defense mechanisms for AI agents and large language models.
Develop formal verification methods and theoretical frameworks to prove security properties and safety guarantees in agentic AI systems.
Publish research findings in top‐tier academic conferences and journals, contributing to the broader scientific understanding of AI security.
Collaborate with academic partners and the research community to advance the state‐of‐the‐art in adversarial robustness and trustworthy AI systems.
Minimum Qualifications PhD in Computer Science, Engineering, Mathematics, or a related field with a focus on machine learning, security, or formal methods.
Strong publication record in top‐tier conferences or journals in AI security, adversarial machine learning, robustness, or formal verification (e.g., NeurIPS, ICML, ICLR, IEEE S'P, USENIX Security, CCS).
Proficiency in Python and experience with at least one additional programming language such as C++, Julia, or Rust for implementing research prototypes.
Preferred Qualifications Deep expertise with modern ML frameworks including