🇮🇹 PhD Positions in Mechanistic Interpretability

Location: Italy

Fully-funded PhD positions in Mechanistic Interpretability and Neurosymbolic NN

We are offering fully-funded Ph.D. positions in Mechanistic Interpretability and Neurosymbolic NN by-design at the University of Rome Tor Vergata, Italy.

The positions are part of the MeMo project, which aims to build alternative ways to build transparent Large Language Models by explicitly using Associative Memories.

• Position 1: Mechanistic Interpretability by-design in Neural-Network-based Large Language Models
• Position 2: Injecting Neuro-symbolic Natural Language Processing Capabilities in Neural-Network-based Large Language Models

To determine if you are a good fit for the position, take this test: test and book an informal chat.

Tags: PhD positions, Mechanistic Interpretability, Neurosymbolic NN, Large Language Models, Data Science, University of Rome Tor Vergata, Italy