Erreiche dein Karriereziel als Data Scientist for Digital Oncology bei Deutsches Krebsforschungszentrum in Heidelberg

Deutsches Krebsforschungszentrum

Position: Data Scientist for Digital Oncology

Department: Junior Research Group Digital Biomarkers for Oncology

Code number: 2021-0295

The German Cancer Research Center is the largest biomedical research institution in Germany. With more than 3,000 employees, we operate an extensive scientific program in the field of cancer research.

So far, AI-based diagnostics have only entered clinical and especially oncological practice to a very limited extent. In the KI Translation Initiative (KTI), our interdisciplinary working group aims to optimize algorithms generated by means of deep learning as diagnostic assistance systems for clinicians in order to enable long-term "tailor-made" care for cancer patients, e.g. with malignant melanoma, breast cancer or prostate cancer. We use image analysis algorithms to analyze hematoxylin-eosin-stained tissue sections in order to enable statements about tumor properties as biomarkers.

The main focus of the project is to achieve an improved generalization ability of such algorithms on "foreign" data - for example on tissue sections from another clinic. In addition, interpretability / explainability of the "black box" CNN for the user will have to be increased in order to enhance usefulness and acceptance of such applications in the clinic. Model uncertainty will also be included in order to provide a further measure of the reliability of the diagnosis made by the algorithm. In addition, the project will also investigate whether the use of XAI methods may serve to identify new structures on histological slides that can also be detected by human observers and thus could also be employed by pathologists to examine tissue sections.

To support our team at DKFZ Heidelberg, we are looking for a data scientist to help develop and scientifically present the newly generated or improved, digital biomarkers.

Job description:

As a member of our team, you will independently research and implement processes to improve the explainability and generalization of neural networks. You will also generate your own scientific publications based on your results and actively support the interdisciplinary team regarding further research questions.

Requirements:

Successfully completed university studies (master's / diploma) with a computer science background
Passion for “Research for a Life without Cancer”
Previous experience in the field of machine learning
Very good Python knowledge
Practical experience with PyTorch, TensorFlow, Keras or Scikit-learn
Ability to work both in a team and independently
Talent for organization as well as a high degree of flexibility and commitment
Ideally, previous experience in the AI areas of explainability, uncertainty and/or generalization

We offer:

Interesting, versatile workplace
International, attractive working environment
Campus with modern state-of-the-art infrastructure
Salary according to TV-L including social benefits
Possibility to work part-time
Flexible working hours
Comprehensive further training program

Earliest Possible Start Date: as soon as possible

Duration: The position is initially limited to 2 years with the possibility of prolongation.

The position can in principle be part-time.

Application Deadline: 01.10.2021

Contact:

Achim Hekler
Phone +49(0) 6221/42-5307

Please note that we do not accept applications submitted via email.

The DKFZ is committed to increase the proportion of women in all areas and positions in which women are underrepresented. Qualified female applicants are therefore particularly encouraged to apply.

Among candidates of equal aptitude and qualifications, a person with disabilities will be given preference.

To apply for a position please use our online application portal (https://www.dkfz.de/en/stellenangebote/index.php).

We ask for your understanding that we cannot return application documents that are sent to us by post (Deutsches Krebsforschungszentrum, Personalabteilung, Im Neuenheimer Feld 280, 69120 Heidelberg) and that we do not accept applications submitted via email. We apologize for any inconvenience this may cause.