Postdoc Position in Neuro-morphic Reinforcement Learning

Postdoc Position in Neuro-morphic Reinforcement Learning

SDU - University of Southern Denmark

Odense, Denmark

About the Project:

The successful candidate will advance the algorithmic and theoretical foundations of reinforcement learning applied to complex, high-dimensional dynamical systems. The project focuses on the intersection of deep reinforcement learning, probabilistic modeling, and bio-inspired architectures (such as Spiking Neural Networks) to achieve sample- and energy-efficient robust and adaptive control under uncertainty and non-stationarity. The postdoc will be responsible for proving theoretical guarantees (e.g., convergence, stability, or sample complexity) for control tasks in non-stationary environments with application to adaptive robotic systems and embodied AI, while translating these insights into scalable, high-fidelity simulation implementations.

Research Environment:

IMADA uniquely brings mathematicians and computer scientists together within a single department to foster theoretically well-backed, high-quality data science research. The department is home to numerous externally funded research projects, and the Data Science and Statistics Group serves as a vibrant synergy platform for experts across fields. The successful candidate will join the ADIN Lab, collaborate on publishing at top-tier venues (NeurIPS, ICML, ICLR, AISTATS), and fulfill standard teaching assistantship duties.

Expected Skills and Qualifications:

We are seeking a candidate with a strong desire to make significant contributions to fundamental machine learning research, possessing a combination of mathematical maturity and advanced engineering skills:

• Education: A PhD in Computer Science, Mathematics, Statistics, or Theoretical Physics at the time of employment;
• Publication Track Record: At least two first-author research papers at flagship venues of core machine learning research (e.g., NeurIPS, ICML, ICLR, AISTATS);
• Theoretical Rigor: A deep understanding of reinforcement learning foundations, with the ability to perform convergence and finite-sample analysis of complex, non-linear continuous control algorithms;
• Implementation Expertise: Outstanding scientific programming skills (Python, PyTorch/JAX) with a proven track record of developing, debugging, and scaling complex RL pipelines or custom simulation environments. Clean public repositories or released source code from past publications is a strong plus;
• Algorithmic Breadth: Familiarity with probabilistic machine learning, distributional reinforcement learning, or bio-inspired neural architectures is highly desirable;
• Communication: Excellent spoken and written communication skills in English.