Research Scientist, Foundation Model

About the role

You will lead research on the foundation model of the physical world for autonomous security systems. The role involves developing probabilistic site memory and world models that predict states in latent space to identify anomalies. You will work closely with perception and model engineers to transition research results directly into production.

Responsibilities

• Develop a learned, probabilistic model of each site to track people, vehicles, and robots.
• Replace rule-based alerting with measured surprise to detect anomalies.
• Post-train open world-model weights on multi-sensor field sequences using latent space prediction.
• Transfer learned representations across different sites and domains.
• Define research questions, design experiments, and validate results for production deployment.

Required skills

• Machine Learning
• Computer Vision
• Robotics
• World models
• Self-supervised learning
• Probabilistic modelling
• Spatio-temporal modelling
• Anomaly detection
• PyTorch

Nice to have

• Scene graphs
• Multi-object tracking
• Trajectory forecasting
• Bayesian deep learning
• Embodied AI
• Simulation

Qualifications

• PhD in machine learning, computer vision, robotics or a related field
• First-author publications at top venues

Benefits

• Equity package

About the Company

Laelaps AI is a founding team based in Zurich building intelligent software for physical security. They focus on enabling robots and sensors to handle critical tasks through an orchestration layer for autonomous systems.