Ph3Job Information /h3 pbOrganisation/Company /b: Spindox Labs srl /p pbResearch Field /b: Computer Science, Artificial Intelligence, Data Engineering, Cyber-Physical Systems, Energy CPS /p pbPositions /b: PhD Position /p pbCountry /b: Italy /p pbApplication Deadline /b: 05/12/2025 – 16:00 (Europe/Rome Time) /p pbType of Contract /b: Permanent /p pbJob Status /b: Full-time /p pbHours Per Week /b: 40 /p pbIs the job funded through the EU Research Framework Programme? /b: Horizon Europe – MSCA – Doctoral Network /p pbMarie Curie Grant Agreement Number /b: /p h3Offer Description /h3 pSpindox Labs srl is seeking to appoint one Doctoral Candidate (DC) to join the Marie Skłodowska-Curie Doctoral Network GREET – Generative Explainee-aware Explainability and Transparency in Proactive Cyber-Physical Eco-Environments. /p h3The Role /h3 pThe DC will contribute to the design, development, and validation of Digital Energy Twin (DET) solutions in energy networks, integrating AI, IoT, and cloud-edge computing to enable resilient, adaptive, transparent, and explainable CPS. /p pThe position will bridge academic excellence at University of Antwerp (UAntwerp – IDLab) and applied research at Spindox Labs, focusing on the energy domain while contributing to GREET’s core objectives of Generative Learning Cognitive Services (GLCS), eco-cognition, proactivity, and explainee-aware explainability. /p pThe selected candidate will be required to undertake the following planned secondments: Edinburgh Napier University (United Kingdom) – Integration with the GREET architecture and frameworks (3 months); and University of Antwerp (Belgium) – Development of explainability twins for cyber-physical systems (4 months). /p h3Scientific Context /h3 pThe research aligns with GREET’s vision of creating next-generation CPS combining eco-cognition, explainability, and proactive decision-making across cloud-edge-IoT environments. At Spindox, the research will focus on energy applications, leveraging digital twin architectures, predictive analytics, neuro-symbolic learning, and generative explainability to support adaptive, transparent, and sustainable energy CPS. /p h3Research Objectives and Expected Results /h3 ul liDesign and Implement Digital Energy Twin Models: Develop real-time monitoring, forecasting, and interactive models within energy CPS, resulting in AI-driven Digital Twin prototypes for enhanced energy grid resilience, load management, and demand response. /li liDevelop AI/ML Pipelines: Build solutions for time-series forecasting, demand flexibility, anomaly detection, and proactive decision-making, leading to validated, proactive, and explainable CPS solutions for Digital Energy Twin use cases. /li liIntegrate Eco-Cognition and Explainability: Incorporate models developed in collaboration with UAntwerp to enhance transparency and adaptability, contributing to GREET’s research agenda on transparent, proactive, and eco-cognitive CPS. /li liFuse Multi-Modal Data: Combine data from energy production/consumption, IoT sensors, mobility, and environmental sources to create predictive and adaptive models, leading to open-source tools, demonstrators, and publications that align with GREET’s dissemination and training goals. /li liApply Neuro-Symbolic Learning and Generative Explainability: Implement GREET’s advanced AI frameworks in energy CPS scenarios, pushing the boundaries of explainable and adaptive systems while producing meaningful contributions to ongoing research and development efforts. /li /ul h3Duties And Responsibilities /h3 ul liConduct applied research at the intersection of AI, IoT, and CPS, under joint supervision from Spindox and UAntwerp. /li liDevelop data engineering pipelines and testbeds for Digital Energy Twin demonstrators. /li liCollaborate with GREET doctoral candidates on shared research challenges: eco-cognition, explainability, and proactivity. /li liContribute to GREET deliverables, reports, and standardization activities. /li liPublish in top-tier journals and conferences; contribute to open-source projects. /li liParticipate in GREET training events, workshops, and industry collaborations. /li liSupport knowledge transfer between academia and industry, including public engagement and dissemination. /li /ul h3Profile /h3 h3Education Background /h3 ul liMaster’s degree in Computer Science, AI, Data Engineering, Electrical Engineering, or a related field. /li liStrong knowledge of AI/ML techniques for time-series forecasting, anomaly detection, and clustering. /li liFamiliarity with IoT, Cyber-Physical Systems (CPS), and digital twin architectures. /li /ul h3Technical Expertise /h3 ul liProficient in Python, Pandas, Scikit-learn, and PyTorch. /li liExperience with distributed computing and data engineering stacks. /li liKnowledge of cloud-edge deployments, containerization, and real-time simulation tools. /li liExpertise in multi-modal sensor integration. /li /ul h3Research Innovation Experience /h3 ul liPrevious experience in EU-funded projects (H2020, MSCA, Horizon Europe) is a plus. /li liProven track record of publications, deliverables, or open-source contributions. /li /ul h3Desirable Skills /h3 ul liFamiliarity with large language models (LLMs), agentic AI, and semantic technologies (e.g., RDF, knowledge graphs). /li liAwareness of dataspaces and data governance frameworks (e.g., Eclipse Dataspace Connector). /li /ul h3What We Offer /h3 ul liDoctoral candidates will receive a competitive remuneration package in accordance with the MSCA allowances, as outlined in the MSCA Work Programme 2023–2025. In addition, funding will be provided for technical and personal skills training, as well as for participation in international research events. These benefits will apply for the full duration of the MSCA-DN grant (36 months). For any period beyond this duration, remuneration will be determined based on the standard salary policy of Spindox Labs employees, excluding any additional allowances provided under the MSCA-DN grant. /li liThe planned start date is March 2026 or as soon as possible after that date. /li /ul h3How To Apply /h3 pYou can apply for this vacancy through the Spindox’s online job application platform up to b05 December 2025 /b (by 16:00 Europe/Rome time). Submit your application using the form “bSubmit your CV /b”. As only one file can be uploaded, kindly combine all documents into a single PDF file before submission. Applications must include: /p ul liMotivation letter highlighting expected impact on your future career. /li liAcademic CV, including transcript and publications. /li liTwo reference letters with contact details. /li liEnglish proficiency certificate. /li liShort research proposal (max. 4 pages, excluding references) integrating: /li liPropose a topic that integrates the position’s core research (i.e., Generative, Explainee-Aware Explainability for Eco-Cognition) with at least one target domain (flexibility approaches for smart energy grids, renewable energy optimization, digital energy twin systems, energy storage management, demand-response forecasting, sustainable energy management). The research proposal should include: (i) problem statement motivation, (ii) expected novelty/impact, (iii) brief approach (models, data/testbeds), (iv) evaluation plan, and (v) alignment with Spindox Labs’ focus on AI-driven energy solutions, digital twin architectures, and proactive CPS for energy networks. /li liThe selection committee reviews all applications as soon as possible after the application deadline. As soon as a decision is made, we will notify you. If you are still eligible after the pre-selection, you will be informed about the possible next step(s) in the selection procedure. /li liIn case of any questions about the online application form, please send an email to:. If you have any questions about the job itself, please contact bLuca Capra /b ( ) and bMario Conci /b ( ). /li /ul h3Eligibility /h3 ul liCandidates must not have resided or carried out their main activity (work, studies, etc.) in Italy for more than 12 months in the 36 months immediately prior to their date of recruitment. /li liCandidates must not already hold a doctoral degree. /li /ul /p #J-18808-Ljbffr