ML Research Engineer: Grid AI & Power Systems

Join; Wien; Hybrid; EUR 65.000 - 90.000; Vollzeit

Benefits dieser Stelle

Hybrid work

R&D budget and conference support

Open-source Maze enhancements

Vienna office in central district

Klimaticket

Zusammenfassung

enliteAI is seeking an ML Research Engineer to develop methods for energy applications and carry them from literature to production-ready systems. You will address state estimation, forecasting, and constraint evaluation for distribution grids, working across research and engineering to deploy MVPs.

The role blends exploration with practical deployment in a hybrid setup in Vienna. You will join a team combining reinforcement learning, optimization, and power systems with a focus on real data and

Qualifikationen

• Strong ML/RL background with ability to translate literature into production-ready methods.
• Experience applying ML to energy/infrastructure domains is highly valued.
• Proven ability to design rigorous experiments and produce reproducible results.

Aufgaben

• Develop ML/RL methods for grid operation problems and build MVPs from prototypes.
• Collaborate across ML, power systems, and data engineering to deploy production-ready solutions.
• Contribute to Maze and extend it toward energy applications.
• Own the model-facing side of data pipelines and ensure schema contracts.

Kenntnisse

Fluent English

Deep ML/RL expertise

Python

PyTorch

Software engineering

Self-directed

Team collaboration

Ausbildung

PhD or related field

Equivalent practical experience

Tools

PyTorch

pandapower

PyPSA

OpenDSS

Grid2Op

Python

Jobbeschreibung

enliteAI is seeking an ML Research Engineer to develop methods for energy applications and carry them from literature to production-ready systems. You will address state estimation, forecasting, and constraint evaluation for distribution grids, working across research and engineering to deploy MVPs.

The role blends exploration with practical deployment in a hybrid setup in Vienna. You will join a team combining reinforcement learning, optimization, and power systems with a focus on real data and