Key Skills

Job Description

We believe organisations can make better decisions when they have a clearer understanding of how people, groups and information behave. We have built an AI platform that uses global social data and signals to understand how narratives propagate, where influence actually sits, how groups cohere and fracture, and when apparent coordination is real. As we grow, we’re looking for Network and Behavioural Scientists with experience in Computational Social Science and Network Analysis to join our team. You’ll work alongside computational social science PhDs and ML specialists to: Analyse complex social networks to understand structure, communities, influence and relationships. Model how narratives and behaviours propagate through networks using diffusion, cascade and contagion models. Develop measures that distinguish structural prominence from actual influence. Detect coordinated behaviour through temporal synchrony, co-occurrence, shared resources and network structure. Develop and validate new network methods where existing approaches fall short. Requirements We’re looking for strong foundations in network analysis particularly community detection, statistical inference on networks, temporal and multilayer networks, bipartite structures, generative and latent-space models, and null/configuration models. You should also have experience with propagation/diffusion, inference from incomplete or partially observed networks, method development and Python. A PhD/Master’s in Network Science, Computational Social Science, Statistical Physics, Applied Mathematics, CS or equivalent industry research experience is ideal. If you want to use network science to understand real human behaviour at scale, develop methods rather than simply apply them, and see your research become part of working AI systems, we’d love to hear from you.

Core Responsibilities

Analyze complex social networks to identify structure, communities, influence, and relationships, and model how narratives and behaviors spread. Develop and validate network methods, distinguish prominence from influence, and detect coordinated behavior using temporal and structural signals.

Requirements

Candidates should have strong network analysis foundations, including community detection, statistical inference, temporal and multilayer networks, generative and latent-space models, and propagation modeling. Experience with incomplete networks, method development, and Python is expected; a relevant PhD or master's degree, or equivalent industry research experience, is ideal.