Post-Doctoral Research Visit F/M Neurosymbolic Relational Graph Neural Networks

Join TYREX to incorporate database schemas, constraints and rules into relational graph-neural-network message passing. The project investigates neurosymbolic aggregation and relational routes, creates annotated benchmarks, and evaluates accuracy, robustness, data efficiency and interpretability. The renewable 12-month appointment has a planned start on 1 December 2026 and gross monthly pay of EUR 2,788. Telework may be possible after six months.

A PhD or equivalent is required. The role focuses on relational learning, graph neural networks and symbolic knowledge. Applications use Inria’s online system. Authorisation may be necessary for a restricted research area.