Postdoctoral Researcher (f/m/d) in Computer Science or Statistics Part-time NEW

Postdoctoral Researcher In Computer Science Or Statistics

The research group for machine learning and artificial intelligence is looking for a postdoctoral researcher in computer science or statistics with a focus on statistical calibration of machine learning models for weather prediction and climate science. You will join the world model of our world project, an interdisciplinary team of around 20 researchers developing a novel AI world model of the earth system. The position will be based in the machine learning and artificial intelligence group at karlsruhe institute of technology (kit) and the heidelberg institute for theoretical studies heidelberg (hits) led by jun.-prof. dr. jan stühmer, in close collaboration with prof. dr. peer nowack (kit) and prof. dr. tilmann gneiting (kit & hits). Place of work will be at the heidelberg institute for theoretical studies in heidelberg.

The wow project, funded by the carl-zeiss-foundation, will develop a modular AI world model to simulate the process chain from long-term changes in global climate to local impacts on societies and ecosystems. As part of the project we aim to bridge the gap between medium-range weather forecast models and long-term climate models. The central topic of our research efforts will be the statistical calibration of machine learning models for weather forecasting, and the statistical calibration of multi-modal machine learning models. To this end, we will develop novel statistical calibration techniques for machine learning models based on proper scoring rules. In an adjunct research project, we are investigating the statistical calibration of generative machine learning models.

Your role

• Conduct cutting-edge research in machine learning on statistical calibration of machine learning-based predictions
• Publish your research findings at major machine learning conferences such as neurips, icml, iclr, and high impact journals.
• Collaborate with other members of the research group
• Supervision of research interns, bachelor- and master-students.

Your profile

• PhD in machine learning, statistics or a related field such as computer science, mathematics, or physics
• Theoretical knowledge in statistical calibration and machine learning
• Publications at conferences such as neurips, icml, iclr, aistats, or relevant journals
• Theoretical understanding and practical experience in statistical calibration of machine learning predictions
• Experience in building prototypes in machine learning frameworks such as pytorch and tensorflow
• Experience with large-scale machine learning models for weather prediction beneficial but not required

If you are not familiar with all of the above – this position provides the perfect opportunity to gain experience in the remaining fields. The environment of this job

• An english-speaking international and thriving work environment
• Access to our own high-performance computing infrastructure and to national high-performance computing infrastructure
• You will work within a highly motivated team of individual researchers in a collaborative working environment
• We provide an interdisciplinary research environment and lots of opportunities for interdisciplinary collaboration
• Strong international connections to world leading academic research institutions (cambridge, mit, edinburgh, eth zurich) and research labs in industry (microsoft research, google deepmind, samsung ai).
• This is a temporary position with an initial 2-year contract.

Application details

Applications should be written in english or german and contain

• Cover letter, including your motivation
• Curriculum vitae with full publication list
• Relevant academic certificates
• Summary of research accomplishments
• Names and contact information for two references

We offer

• Science for impact: engage with topics of societal relevance — in an excellent scientific environment that enables change.
• Flexible working hours: take advantage of flexible‑hours schemes, remote‑work options, part‑time models, and a 30‑day annual leave entitlement to achieve an optimal work‑life balance.
• Career‑building and developmental opportunities: we provide you with a structured onboarding program, a broad spectrum of continuing‑education options, and personalised support, thereby fostering your individual growth.
• Family-friendliness: the “kit‑family +” program assists you in reconciling work and family life by offering childcare services, holiday activities, a parent‑child office space, and assistance with caring for relatives.
• Stay healthy: under the motto “fit at kit – body, mind and soul,” we promote your well‑being through fitness classes, mental‑health programmes, and regular preventive health examinations.
• Individualised extra benefits: enjoy a corporate pension (vbl), a €25 monthly contribution toward a jobticket bw, plus a broad selection of cultural and recreational programmes.