🇬🇧 Research Fellow – Deep Learning Theory & AI Safety

Location: United Kingdom
Deadline: 26 March 2026

Postdoctoral training fellowship available at Saxe Lab for research on deep learning theory and AI safety. Apply by 26 March 2026.

A postdoctoral training fellowship is available under Professor Andrew Saxe’s guidance at the Saxe Lab, focusing on deep learning theory and AI safety.

• Research into artificial deep networks using applied mathematics and statistical physics.
• Understanding depth’s impact on learned representations and network behavior.
• Applications to AI safety, including emergent misalignment and safety fine-tuning.

For more information and to apply, visit UCL Job: B02-10169.

Tags: Deep Learning Theory, AI Safety, Postdoctoral Fellowship, Research Fellow, Artificial Neural Networks, Machine Learning, United Kingdom