Postdoc: Tabular Foundation Models for Energy Systems

1000scholars; Dübendorf; On-site; CHF 90,000 - 120,000; Full time

Job summary

Empa – Swiss Federal Laboratories for Materials Science and Technology in Dübendorf, Switzerland, invites applications for a Postdoctoral Researcher position focused on tabular foundation models for building and district energy systems. The role develops and benchmarks models, adapts them to energy tasks, and coordinates with UESL and IMOS to push research outcomes.

The ideal candidate holds a PhD in a related field with strong ML expertise, experience in foundation models, and excellent

Qualifications

• PhD in mathematics, electrical or mechanical engineering, computer science, or related field.
• Strong ML background with foundation models, evaluation, adaptation, fine-tuning.
• Experience with tabular foundation models or structured data is highly relevant.
• Excellent English, both written and spoken.

Responsibilities

• Evaluate and benchmark existing pre-trained tabular foundation models for energy applications.
• Adapt and fine-tune models for energy-system tasks using domain data.
• Develop new tabular foundation-model approaches for heterogeneous energy datasets.
• Validate models with building measurements, physics-based simulations and energy-system optimization models.
• Investigate usage in prediction, surrogate modeling, uncertainty quantification, and decision support.
• Coordinate research activities between UESL and IMOS.
• Publish and present research perspectives and results.
• Contribute to research proposals and funding applications.

Skills

Deep learning

Foundation models

Pre-trained models

Fine-tuning

Transfer learning

Self-supervised learning

Python programming

Research codebases

ML track record

English communication

Education

PhD (math/EE/CS/related)

Tools

Python

Job description

Empa – Swiss Federal Laboratories for Materials Science and Technology in Dübendorf, Switzerland, invites applications for a Postdoctoral Researcher position focused on tabular foundation models for building and district energy systems. The role develops and benchmarks models, adapts them to energy tasks, and coordinates with UESL and IMOS to push research outcomes.

The ideal candidate holds a PhD in a related field with strong ML expertise, experience in foundation models, and excellent