MEHRAN  HOSSEINI

I'm a lecturer (assistant professor) in the Department of Computer Science at the University of Manchester and a member of the Autonomy & Verification Group. My research is on the intersection of Formal Methods and Artificial Intelligence (AI). I'm interested in the mathematical foundations of safe and verifiable AI systems, with a focus on developing scalable verification algorithms and novel deep learning architectures (neuro-symbolic and neural architectures) that are verification-friendly yet as or more capable than the state-of-the-art.

Previously, I was a postdoctoral researcher at King's College London's Informatics Department. At the King's, I led the research on safety verification of autonomous neural agents as part of the EU Horizon's REXASI-PRO project, collaborating with Nicola Paoletti and DDV Lab. Before joining KCL, I was at Imperial College London's Safe Artificial Intelligence Lab (SAIL) collaborating with Alessio Lomuscio on scalable verification of Recurrent Neural Nets (RNNs). Prior to this, I completed my DPhil in computer science at Oxford University, where I solved the universal termination problem for linear loop programs, showing it is decidable. At Oxford, I was lucky to have James Worrell and Joël Ouaknine as my supervisors.

Working with Me

I'm looking for motivated PhD students with strong backgrounds in either computer science/engineering or mathematics to join my lab. It would be a bonus if your background is in formal methods or AI. If you are interested, please send me a short (300 words) email titled "PhD Application: [Your Name]". Please include your CV and two paragraphs on why you think your background and research interest and plans align with mine.

I'm also supervising for the Marie Skłodowska-Curie Actions Postdoctoral Fellowship at UoM. If you are interested in applying for the upcoming call, please get in touch.

  firstname.lastname_at_manchester.ac.uk