Scientific Researcher (f/m/d) AI-Based Replacement of Chemistry-Climate Simulations with a Math[...]

Internetchemie; Karlsruhe; Vor Ort; EUR 30.000 - 35.000; Teilzeit

Zusammenfassung

A leading research organization in Karlsruhe is seeking a Scientific Researcher (f/m/d) to develop AI-based replacements for climate simulations in a mathematics-focused role. Ideal candidates will have a master's in mathematics and experience with deep learning frameworks. The position offers a chance to earn a doctoral degree while working in a flexible, family-friendly environment. Applications are welcome until November 28, 2025.

Leistungen

Wide range of training opportunities

Flexible, family-friendly working time models

Qualifikationen

• PhD position in an AI research project requiring a master's in mathematics.
• Familiarity with AI models and deep learning frameworks essential.
• Strong team collaboration and communication skills are needed.

Aufgaben

• Develop an AI model to replace chemistry-climate simulations.
• Analyze AI-based and traditional ESM simulations.
• Conduct theoretical analysis on hyperparameter optimization.

Kenntnisse

Knowledge of current deep learning frameworks (e.g., PyTorch or TensorFlow)

Interest in optimization theory

Strong communication and presentation skills

Ability to work and publish scientifically

Good communication skills in German or English

Ausbildung

Completed master’s studies in mathematics

Jobbeschreibung

Scientific Researcher (f/m/d) AI-Based Replacement of Chemistry-Climate Simulations with a Mathematical Focus on Model Understanding and Optimization

PhD Position at Faculty of Mathematics – 75 % part-time (start: February 1, 2026, limited up to 3 years).

The Scientific Computing Center (SCC) is a central scientific institution at KIT that performs tasks related to research, teaching, and innovation and provides comprehensive services within KIT and to external parties.

This research project focuses on the application of AI models in Earth System Science. You will work on efficiently replacing the chemistry‑climate simulation from an Earth System Model (ESM) with an AI‑based approach and develop mathematically rigorous methods for interpretable AI modeling and systematic hyperparameter optimization. In detail:

• Develop a concept to replace the chemistry climate simulation of the ESM with a suitable AI model, including testing and selecting appropriate AI architectures (e.g., RNNs, CNNs, PINNs, Transformers), identifying relevant input features, applying dimensionality reduction techniques, and performing hyperparameter tuning (learning rate, number of layers, regularization strength).
• Train the AI model using a dataset from long‑term ESM simulations (1979‑2024), followed by running simulations with the trained AI model.
• Conduct a comparative analysis of AI‑based simulations versus traditional ESM simulations, assessing accuracy and performance.
• Advance beyond a black‑box approach by achieving a mathematical understanding of the AI model, developing systematic methods for optimizing hyperparameter tuning based on principles of optimization theory, statistical learning theory, and explainable AI.
• Perform theoretical analysis of hyperparameter optimization—including studying convergence properties, regularization effects, and sensitivity analysis—which constitutes the core mathematical challenge of the project.

The position offers the opportunity to earn a doctoral degree while working in the CSMM research group led by Prof. Dr. Martin Frank and being part of KIT’s KCDS graduate school.

Personal Qualifications

• Completed master’s studies in mathematics.
• Knowledge of current deep learning frameworks (e.g., PyTorch or TensorFlow) and AI models.
• Interest in optimization theory, statistical learning theory, or explainable AI.
• Ability to work and publish in a targeted and scientific manner.
• Strong communication and presentation skills, willingness and ability to work in a team.
• Good communication skills in German or English.

The SCC offers an exciting and varied job within an agile team and a wide range of training opportunities and flexible, family‑friendly working time models.

We prefer to balance the number of employees (f/m/d). Therefore we kindly ask female applicants to apply for this job.

Recognized severely disabled persons will be preferred if they are equally qualified.

Application

We look forward to receiving your application, including motivation letter, CV, and certificates, online until November 28 2025 using vacancy number 447/2025. Direct your application to Mr. Dominik Meschar, Karlsruhe Institute of Technology (KIT), Human Resources, Hermann‑von‑Helmholtz‑Platz 1, 76344 Eggenstein‑Leopoldshafen, Germany. For further information, contact Dr. Ole Kirner ([e-mail]) or Dr. Jasmin Hörter ([e-mail]).

Further information about the SCC can be found on the SCC website. Processing of your personal data by KIT will be subject to this Privacy Policy. Visit www.kit.edu for more information.