Postdoc: Tabular Foundation Models for Building Energy

Empa; Dübendorf; Vor Ort; CHF 110.000 - 140.000; Vollzeit

Benefits dieser Stelle

Interdisciplinary environment

Collaboration with EPFL

Competitive research funding

Flexible starting date

Zusammenfassung

Empa, in collaboration with EPFL, seeks a postdoctoral researcher to advance tabular foundation models for energy systems. You will evaluate, adapt, and extend pre-trained models across buildings and district-scale energy data, enhancing transferability and performance through domain-specific knowledge.

The role combines Empa's energy-system modelling expertise with IMOS's ML focus, enabling cutting-edge research with real-world impact. Strong ML, Python, and English communication are essential.

Qualifikationen

• PhD required in a quantitative field with strong ML background.
• Demonstrated research experience with foundation models and fine-tuning strategies.
• Experience with tabular foundation models or foundation models for structured data.
• Excellent written and spoken English.

Aufgaben

• Evaluate and benchmark pre-trained tabular foundation models for building- and district-scale energy apps.
• Adapt and fine-tune foundation models for energy-system data and domain knowledge.
• Develop new tabular foundation-model approaches focusing on transferability across heterogeneous energy systems.
• Validate and benchmark models using building measurements, physics-based simulations and optimization models.
• Investigate how tabular foundation models can support energy-system modelling and optimization.
• Coordinate joint research activities between UESL and IMOS.
• Publish and present research perspectives and results.
• Contribute to research proposals and funding opportunities.

Kenntnisse

Foundation models

Deep learning

Python programming

Machine learning research

English proficiency

Ausbildung

PhD in mathematics, electrical or mechanical engineering, computer science or related field

Jobbeschreibung

Empa, in collaboration with EPFL, seeks a postdoctoral researcher to advance tabular foundation models for energy systems. You will evaluate, adapt, and extend pre-trained models across buildings and district-scale energy data, enhancing transferability and performance through domain-specific knowledge.

The role combines Empa's energy-system modelling expertise with IMOS's ML focus, enabling cutting-edge research with real-world impact. Strong ML, Python, and English communication are essential.