Postdoc in Neuro-Symbolic Federated Learning with Secure Multi-Party Computation at the IT University of Copenhagen

This postdoctoral position focuses on advanced research at the intersection of neuro-symbolic learning, federated learning, and secure multi-party computation. The ideal candidate will possess deep expertise in machine learning, particularly in neuro-symbolic methods that combine neural networks with symbolic reasoning to enhance interpretability and robustness. Experience in federated learning is essential, emphasizing distributed model training across multiple decentralized devices or servers while preserving data privacy. Proficiency in secure multi-party computation techniques is critical to ensure privacy-preserving collaborative computations without exposing sensitive data. The role requires strong foundations in cryptographic protocols, privacy-preserving algorithms, and distributed systems. Candidates should have a proven research background, ideally demonstrated through publications in top-tier conferences or journals related to machine learning, security, or privacy. Familiarity with programming languages commonly used in machine learning research, such as Python, and frameworks like TensorFlow or PyTorch, is expected. Knowledge of cryptographic libraries and tools supporting secure computation will be advantageous. The position is based at the IT University of Copenhagen, indicating a collaborative academic environment with opportunities for interdisciplinary work. Overall, the candidate should combine theoretical knowledge with practical skills in implementing and evaluating complex algorithms in privacy-sensitive, distributed learning contexts, demonstrating strong analytical, problem-solving, and communication abilities suitable for a postdoctoral research role.