PhD student on perceptual foundation models

**Job Description**
This PhD project focuses on developing a new generation of perceptual foundation models to address limitations of current language-focused models, which hinder spatial reasoning, temporal logic, and low-resource operation, leading to shortcut learning and hallucination. The goal is to contribute advanced perceptual pre-training and fine-tuning algorithms that expand sensing abilities, generalize effectively at deployment, and operate efficiently and sustainably. The research is embedded in the Video & Image Sense lab at the University of Amsterdam and involves active collaboration with partner TNO within the NWO Perspectief Foundation for Industry (FIND) project, which brings together multiple universities, companies, and knowledge institutes to strengthen the Dutch high-tech industry in AI-based automation.

**Skills & Abilities**
• Strong background/knowledge in machine learning and computer vision (natural language processing is a plus).
• Solid mathematics foundations, especially statistics, calculus, and linear algebra.
• Excellent programming skills, preferably in Python.
• Experience with AI/HPC supercomputing and running software on scale.
• Highly motivated, independent, and creative.
• Strong communication, presentation, and writing skills.
• Excellent command of English.

**Qualifications**
Required Degree(s) in:
• Artificial Intelligence
• (Applied) Mathematics/Physics
• Computer Science
• Engineering or related field

**Experience**
Other:
• Prior publications in relevant machine learning or computer vision conferences or journals are advantageous.

Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!