Doctoral or Early Postdoctoral Fellowship Position in Deep Learning for Genomic Sequence Data Einrichtung: Fakultät für Mathematik, Informatik und Statistik (Institut für Statistik) Besetzungsdatum: 01.01.2020 or later Ende der Bewerbungsfrist: 29.02.2020 Entgeltgruppe: E13/E14 Befristung: 3 Jahre Es besteht grundsätzlich die Möglichkeit der Teilzeitbeschäftigung. Die Ludwig-Maximilians-Universität München (LMU) ist eine der renommiertesten und größten Universitäten Deutschlands. Aufgaben Project Description One of the greatest challenges of biology is understanding the complex dynamics of the organization of the genome: the functional relevance of a substantial fraction of the genome still remains to be explored. In collaboration with the Helmholtz Centre for Infection Research (HZI) we try to gain greater insight into the genome by applying unsupervised and semi-supervised deep learning techniques to genomic data. It is unclear which kind of deep learning models would be best suited to model this data. A major part of the project is therefore to use neural architecture search and hyperparameter tuning to find models that perform particularly well. Your Responsibilities: * Active research and publications * Constructing and improving software implementations * Support in teaching in machine learning / deep learning * Supervising students Anforderungen Your Profile: * Degree (Master or PhD level) in computer science, machine learning, statistics, biostatistics, bioinformatics, or a related quantitative field * Excellent knowledge of deep learning, ideally experience with sequential data * Experience with deep learning frameworks (e.g. PyTorch, Tensorflow, or Keras) * Strong programming skills (R, Python, or C++) and experience in working with high-performance computation * Interest in working with genomic data * Eagerness to work with, and, if postdoc, support and supervise a team of highly motivated PhD and graduate students * Fluency in written and spoken English How to apply: Please provide us with: * A short statement letter informing us why you are a good candidate for the position (~ 1 page) * A detailed CV, with special focus on: obtained degrees, taken classes in relevant topics, publications, programming skills / projects, track record * Contact details of two or three academic referees Interested applicants should send these documents in PDF format via email to: Martin Binder, martin.binder@stat.uni-muenchen.de, quoting “Application GenomeNet” in the subject. Please also contact Martin if you have any questions. Ihr Arbeitsplatz befindet sich in zentraler Lage in München und ist sehr gut mit öffentlichen Verkehrsmitteln zu erreichen. Wir bieten Ihnen eine interessante und verantwortungsvolle Tätigkeit mit guten Weiterbildungs- und Entwicklungsmöglichkeiten. Schwerbehinderte Personen werden bei ansonsten im Wesentlichen gleicher Eignung bevorzugt. Die Bewerbung von Frauen wird begrüßt. Weitere Informationen http://www.compstat.statistik.uni-muenchen.de/ Bewerbungsadresse Ludwig-Maximilians-Universität München Geschwister-Scholl-Platz 1 80539 München E-Mail: martin.binder@stat.uni-muenchen.de Ansprechpartner/in Martin Binder If you apply for this position please say you saw it on Bioloxy

Doctoral or Early Postdoctoral Fellowship Position in Deep Learning for Genomic Sequence Data

Einrichtung: Fakultät für Mathematik, Informatik und Statistik
(Institut für Statistik)
Besetzungsdatum: 01.01.2020 or later
Ende der Bewerbungsfrist: 29.02.2020
Entgeltgruppe: E13/E14
Befristung: 3 Jahre

Es besteht grundsätzlich die Möglichkeit der Teilzeitbeschäftigung.

Die Ludwig-Maximilians-Universität München (LMU) ist eine der renommiertesten und größten Universitäten Deutschlands.

Aufgaben

Project Description

One of the greatest challenges of biology is understanding the complex dynamics of the organization of the genome: the functional relevance of a substantial fraction of the genome still remains to be explored. In collaboration with the Helmholtz Centre for Infection Research (HZI) we try to gain greater insight into the genome by applying unsupervised and semi-supervised deep learning techniques to genomic data.

It is unclear which kind of deep learning models would be best suited to model this data. A major part of the project is therefore to use neural architecture search and hyperparameter tuning to find models that perform particularly well.

Your Responsibilities:

* Active research and publications
* Constructing and improving software implementations
* Support in teaching in machine learning / deep learning
* Supervising students

Anforderungen

Your Profile:

* Degree (Master or PhD level) in computer science, machine learning, statistics, biostatistics, bioinformatics, or a related quantitative field
* Excellent knowledge of deep learning, ideally experience with sequential data
* Experience with deep learning frameworks (e.g. PyTorch, Tensorflow, or Keras)
* Strong programming skills (R, Python, or C++) and experience in working with high-performance computation
* Interest in working with genomic data
* Eagerness to work with, and, if postdoc, support and supervise a team of highly motivated PhD and graduate students
* Fluency in written and spoken English

How to apply:

Please provide us with:
* A short statement letter informing us why you are a good candidate for the position (~ 1 page)
* A detailed CV, with special focus on: obtained degrees, taken classes in relevant topics, publications, programming skills / projects, track record
* Contact details of two or three academic referees

Interested applicants should send these documents in PDF format via email to: Martin Binder, martin.binder@stat.uni-muenchen.de, quoting “Application GenomeNet” in the subject. Please also contact Martin if you have any questions.

Ihr Arbeitsplatz befindet sich in zentraler Lage in München und ist sehr gut mit öffentlichen Verkehrsmitteln zu erreichen. Wir bieten Ihnen eine interessante und verantwortungsvolle Tätigkeit mit guten Weiterbildungs- und Entwicklungsmöglichkeiten. Schwerbehinderte Personen werden bei ansonsten im Wesentlichen gleicher Eignung bevorzugt. Die Bewerbung von Frauen wird begrüßt.