The Computational Intelligence and Data Analysis Group (CIDAG) at UNIFESP, São José dos Campos, Brazil, is inviting applications for two postdoctoral research positions focused on Artificial Intelligence (AI) and New Energy systems. These fellowships are hosted within the Center for Innovation on New Energies (CINE), a high-profile multidisciplinary research center funded by Shell and FAPESP. The center provides an advanced, collaborative environment for researchers from computer science, engineering, physics, chemistry, and materials science, working at the intersection of AI, energy, and materials innovation. Candidates will collaborate closely with Prof. Marcos G. Quiles (CIDAG/UNIFESP), Prof. Juarez L. F. Da Silva (IQSC/USP), and Prof. Ronaldo Prati (UFABC). Open Positions 1. Machine Learning for Chemistry and Materials Science This project focuses on developing Machine Learning Force Fields (MLFF) to accelerate Molecular Dynamics simulations. The aim is to use Graph Neural Networks (GNNs) to predict interatomic potentials, reducing the computational cost and time associated with traditional quantum mechanical simulations. Candidate Profile: PhD in Computer Science, Physics, Chemistry, or Materials Science Strong programming skills in Python and PyTorch Interest in materials informatics, computational modeling, and AI-driven simulations Experience with ML model development, data-driven materials design, or computational chemistry is desirable Key Responsibilities: Implement GNN-based MLFF models to predict interatomic potentials Validate ML models against conventional quantum mechanical calculations Collaborate with experimental and computational teams to optimize materials discovery pipelines Publish findings in high-impact journals and present results in conferences 2. Machine Learning for Energy Systems & Device Monitoring This project focuses on predictive modeling for energy systems, including wind turbines and battery/supercapacitor devices. The aim is to develop models for incipient failure detection, State of Health (SOH), and State of Charge (SOC) estimation. Deep learning techniques will be applied to time-series sensor data for anomaly detection and predictive maintenance. Candidate Profile: PhD in Computer Science, Electrical/Mechanical Engineering, or Data Science Expertise in Prognostics and Health Management (PHM), predictive maintenance, or industrial IoT analytics Experience with large-scale sensor datasets, time-series modeling, and deep learning frameworks Skills in Python, TensorFlow, or PyTorch for ML model implementation Key Responsibilities: Develop deep learning models for predicting failure in energy devices Analyze sensor datasets from wind turbines and energy storage systems Collaborate with interdisciplinary teams to integrate predictive models into energy systems Disseminate findings through publications and conferences Fellowship Details Stipend: BRL 9,100/month (tax-free) Duration: 12 months, renewable based on performance Location: UNIFESP (ICT campus), São José dos Campos, Brazil, a leading technology hub FAPESP Opportunity: Candidates with outstanding research records may apply for a FAPESP Postdoctoral Fellowship, offering BRL 12,570/month plus research contingency funds This fellowship provides an excellent platform for early-career researchers to advance their careers in AI-driven energy and materials research, working in a multidisciplinary, high-impact environment. Benefits of the Fellowship Opportunity to work in a world-class research center supported by Shell and FAPESP Exposure to cutting-edge AI applications in energy and materials science Collaboration with renowned researchers and international teams Support for high-impact publications and career development Access to state-of-the-art computational facilities and laboratories How to Apply Applicants must submit the following: CV including a full list of publications Cover Letter (1 page) outlining relevant skills and research interests Contact details for 2 references Applications should be sent to Prof. Marcos G. Quiles at gquiles@unifesp.br, using the subject line: Postdoc Application - [Position 1 or 2] - [Your Name] Deadline: 28 February 2026Expected Start Date: July/August 2026 Ideal Candidates Researchers with a strong background in machine learning, deep learning, and AI applications PhDs who are eager to apply computational intelligence to energy systems or materials science Individuals seeking international research exposure in a collaborative, multidisciplinary environment Candidates interested in high-impact research, publications, and potential FAPESP-funded projects This postdoctoral fellowship represents a unique opportunity to combine AI expertise with new energy and materials research, contributing to sustainable, data-driven solutions for energy transition and materials innovation. Researchers will gain hands-on experience with cutting-edge AI methodologies, work in a multidisciplinary, collaborative setting, and have a platform for career acceleration in academia or industry. For more opportunities such as these please follow us on Facebook, Instagram , WhatsApp, Twitter, LinkedIn and Telegram Disclaimer: Global South Opportunities (GSO) is not the fellowship organization. For any inquiries, please contact the responsible organization directly. Please do not send your applications to GSO, as we are unable to process them. Due to the high volume of emails we receive daily, we may not be able to respond to all inquiries. Thank you for your understanding.