Postdoc: Reinforcement Learning for Epidemic Mitigation

Karlstad University; Elsene; Sur place; EUR 52 000 - 68 000; Plein temps

Avantages offerts par ce poste

Telework allowance

Internet stipend

35 days leave

Hospitalisation insurance

Public transport reimbursement

Bike compensation

Campus meals

Résumé du poste

Vrije Universiteit Brussel (VUB) invites applications for a Postdoctoral Researcher in reinforcement learning for epidemic mitigation. The role focuses on learning-based control of infectious disease spread under realistic constraints, interfacing RL with computational epidemiology.

You will develop multi-objective, hierarchical, and explainable RL methods, with uncertainty-aware decision-making, contributing to policy-relevant research and reproducible workflows.

Qualifications

• PhD in machine learning, AI, CS or related field.
• Experience with reinforcement learning, sequential decision-making, or related ML methods.
• Strong programming skills, preferably Python; experience with JAX is a plus.
• Experience with simulation-based or quantitative research.
• Ability to work independently and in a multidisciplinary team.
• Strong written and oral English communication skills.
• Non‑EEA nationals must obtain a permit for VUB residence.

Responsabilités

• Develop and implement reinforcement learning approaches for epidemic mitigation.
• Work with epidemic simulation models and formulate control problems as sequential decision-making tasks.
• Contribute to scientific publications, software, and reproducible research workflows.
• Present findings at project meetings, conferences, and workshops.

Connaissances

Reinforcement learning

Sequential decision-making

Python programming

JAX

Simulation methods

Formation

PhD in ML/AI/CS

Description du poste

Vrije Universiteit Brussel (VUB) invites applications for a Postdoctoral Researcher in reinforcement learning for epidemic mitigation. The role focuses on learning-based control of infectious disease spread under realistic constraints, interfacing RL with computational epidemiology.

You will develop multi-objective, hierarchical, and explainable RL methods, with uncertainty-aware decision-making, contributing to policy-relevant research and reproducible workflows.