Gain practice in systems, software and data-engineering with a socially relevant application

The CASSANDRA (Clinical ASSist AND aleRt Algorithms in visceral surgery) research project is looking for students to contribute to post-surgery prediction systems. In the scope of this project we collect data from several stages of the surgery process, to accurately predict severe complications. We would like you to assist with, among others, advanced data preprocessing, feature engineering, and building efficient data pipelines.

In this role you will be bridging the gap of computer science and the medical field, and directly work with clinicians and computer science researchers. Your work will be varied, but mainly based on discovery, cleansing, structuring, and transformation of collected data. Ideally, you have experience with ETL (Extract, Transform, Load) paradigm from other projects. You will be building a robust data processing infrastructure that can be executed continuously. The resulting data will be integrated into machine learning applications where data quality is crucial to success.

Your work will contribute to advance research in machine learning applied to medicine. That means that the data you prepare will be used for research that increases the quality and the expectancy of people’s lives. We additionally offer the opportunity to contribute to active research yourself by being a co-author on medical and computer science related research.  

Requirements and Expectations

The position provides a flexible 10-hour work week. Additionally, we prefer the following profile for applicants:

• An interest in scientific applications of data and software systems
• A Computer Science related study, such as: Data Engineering, IT-Systems Engineering, Software Systems Engineering, Cybersecurity, or equivalents
• Experience in Python (preferably also other languages like R, Java, C#, or C++)
  • Ideally some of the following packages: Pandas, NumPy, PySpark, SK-Learn, or equivalents
• Experiencewith data management:
  • Streaming data analytics: Flink, Spark, Storm
  • Hadoop based frameworks
  • Hive, Impala or other SQL-like databases
• Providing occasional on-site assistance at the Charité Virchow clinic
• Most importantly, you are motivated to explore and learn new frameworks and languages to integrate medical data into practice

Please consider that these requirements can be loosely interpreted. Most important is the willingness to learn and develop yourself during your work. Contact us if you have any questions or doubts about the requirements (see below).

What do we offer?

The Charité and Hasso Plattner Institute offer a safe working environment focused on individual development. Additionally, we offer:

• Flexible work schedule and partial freedom in working topics

• Laying the groundwork for extending and improving the lives of patients
• Possibility to gain practical experience with data lakes, computing clusters, and data frameworks
• Options for interesting future theses and projects for advancing your studies
• Possibility contribute to be a co-author of active computer science and medical research
• Student position available and funded until June 2024

Contact

If you are excited about this opportunity and fit the profile above, please reach out to us! In case you have any questions about the position, want to see what is possible, or you are curious about the skills involved, feel free to contact us as well.