Join us in tackling one of the world’s most pressing challenges: making energy systems smarter, more efficient, and more resilient. We’re looking for a Power Systems Engineer with a machine learning background and solid software engineering experience to help develop intelligent control and decision-support systems for future energy infrastructure.

• Develop intelligent optimization and control solutions for next-generation power grids, integrating classic Machine Learning (ML) and Reinforcement Learning (RL) where applicable.
• Contribute to our open-source Maze framework - a simulation-based RL platform - and adapt it to energy and infrastructure applications.
• Explore and adapt state-of-the-art methods (e.g. RL, time-series forecasting, GNNs, hybrid modeling) to industrial-scale power system problems.
• Collaborate with a cross-functional team of ML engineers, researchers, and domain experts on high-impact industry and EU-funded research projects.

• Strong background in electrical engineering, energy systems, grid modeling, or power system operations.
• Excellent Python programming skills and solid software engineering practices.
• Experience with PyTorch and familiarity with optimization methods and ML techniques.
• Hands-on experience with power-grid simulations (PandaPower, OpenDSS, DCSimulation, etc,.), sequential decision-making, or time-series data modeling.
• Degree in electrical engineering, computer science, energy informatics or a related field.
• Familiarity with containerization and distributed computing frameworks (Docker, Kubernetes, Ray).
• Proactive, self-motivated problem solver who enjoys applying ML in meaningful, real-world contexts.

• A research-driven team applying ML and optimization to real-world energy challenges.
• Projects at the interface of academia and industry — enliteAI is part of EU Horizon initiatives like AI4REALNET, AI-EFFECT, and INSIEME.
• Hands-on work in energy-focused applications combining optimization, simulation, and AI.
• Flexible work models: remote-friendly setup, central Vienna office (1st district), and minimal core hours.
• Budget and time for R&D, conferences, and professional development.