Cloud / Data Engineer – Big Data Core (RECOMBINE-X)

The Big Data Core of the Princess Máxima Center is looking for an enthusiastic, highly motivated cloud / data engineer who excels in a stimulating, multi-disciplinary research environment and can play a central role in building the cloud data platform for RECOMBINE-X, an international AI-driven pediatric oncology drug discovery project.

Tasks and responsibilities

As part of Work Package 5 (Data Platform Development and Open-Access PBPK/PD Explorer) of RECOMBINE-X, you will build the technical foundation that connects the project’s physiologically based pharmacokinetic and pharmacodynamic (PBPK/PD) data to our existing cloud-native genomics infrastructure, and enable both fixed dashboarding and flexible, interactive analysis for the consortium and the wider research community. You will work in close collaboration with the RECOMBINE-X consortium – including the R2 platform team at Amsterdam UMC and Medstone Science – as well as with bioinformaticians and IT staff within the Big Data Core.

Specific Tasks Include

• Integrate the RECOMBINE-X pharmacokinetic and pharmacodynamic (PBPK/PD) data into Google BigQuery, a cloud-native data warehouse, which already hosts a large part of the genomic data of the Máxima biobank, as the starting point for downstream access and analysis.

• Contribute to the technical development of the RECOMBINE-X PBPK/PD Explorer (WP5), from internal data management infrastructure to the public, open-access platform, in collaboration with the R2 platform at Amsterdam UMC, Medstone Science, and Dr. Jan Koster.

• Develop and maintain both fixed dashboarding and dynamic, interactive analysis interfaces, connecting with tools such as cBioPortal (dashboarding) and Gen3/NL-4C (requests and access to primary data).

• Build interactive analysis environments, e.g. R Shiny applications or Jupyter notebooks, that allow researchers to develop and run their own analyses on the platform.

• Explore the use of Google Vertex AI for machine learning models on top of the integrated dataset.

• Manage and support access to our Google Cloud environment, enabling researchers to develop and run their own analysis pipelines with maximum flexibility.

• Help define the hosting and compute requirements for RECOMBINE-X analyses, from routine workloads to more computationally intensive analyses.

• Contribute to the general IT architecture and security setup of the platform, including preparation for a security audit.

• Help build insight into the operational and hosting costs of the platform over the course of the project, to inform its long-term sustainability.

Profile

We expect a highly motivated, pro-active candidate with a bachelor’s or master’s degree in computer science, data engineering, or a related field, with experience or a proven interest in cloud and data engineering. Experience in the field of genomics/bioinformatics and (bio)medical data is desirable. Excellent technical skills and hands-on experience with cloud platforms, in particular Google Cloud Platform (BigQuery, and ideally Vertex AI), is required, and knowledge of Python, R, Linux and SQL is highly preferred. A good understanding of data warehouse and pipeline design, and affinity with building dashboards and interactive analysis tools (e.g. R Shiny, Jupyter notebooks) is a plus. The candidate should have good communication skills in Dutch and/or English and be a flexible team player in a dynamic, diverse and international research environment.

Our job offer

We offer a fulltime position (36 hours a week) within the RECOMBINE-X project, dedicated to the development of Work Package 5. You will initially be appointed for the duration of one year, with a possible extension. You will be working in a very stimulating and cross-disciplinary research environment, combining cutting-edge pediatric oncology research with state-of-the-art cloud and information technology platforms. Your gross monthly salary will depend on experience and background, with a maximum of € 6.220,- per month (scale 55 or 60 depending on qualifications and expertise), with 8,33% gross monthly salary holiday allowance and 8,33% end-of-year bonus. The Princess Máxima Center operates according to the collective labour agreement ‘cao algemene ziekenhuizen’.

Organisation

The Princess Máxima Center for Pediatric Oncology is a research hospital concentrating healthcare, research and education of pediatric cancer in a single location in Utrecht. The institute aims to provide the highest level of care for all children with cancer and has the ambition to cure all children of cancer and improve quality of life. The center brings together the best possible care and scientific research, creating a unique interdisciplinary institute for pediatric oncology in Europe.

The candidate will be part of the Big Data Core at the Princess Máxima Center. This unit is responsible for performing and developing bioinformatic data analyses regarding our institute-wide biobanking and clinical genomics activities. The Big Data Core is at the forefront of using next-generation sequencing technologies in research, including exome sequencing (WES), whole-genome sequencing (WGS) and RNA-seq based analyses for all patients, as well as DNA methylation-based classification of brain tumors. We have extensive experience with implementing novel technologies in a mixed diagnostic and research setting, as well as coordinating bioinformatics infrastructures such as High-Performance and Cloud computing, workflow management systems, and data sharing and collaboration facilities. Through RECOMBINE-X, the Big Data Core is now extending this infrastructure towards cloud-based pharmacology and drug-discovery data platforms.

Project

RECOMBINE-X (“An AI-Driven Open PBPK/PD Platform to Accelerate Pediatric Cancer Drug Discovery”) is an international consortium project, led by Dr. Dannis van Vuurden at the Princess Máxima Center, together with the Netherlands Cancer Institute, Amsterdam UMC, UMC Utrecht, the Leiden Academic Centre for Drug Research (LACDR) and Medstone Science. RECOMBINE-X aims to revolutionize pediatric oncology drug discovery by building an open, AI-powered PBPK/PD platform that identifies drug combinations with both proven efficacy and realistic deliverability in children. Rather than focusing purely on molecular or gene-based therapies, RECOMBINE-X integrates pharmacokinetics with pharmacodynamics, to find combinations that are not only effective at the cellular level but also realistically deliverable to pediatric brain and solid tumors at therapeutic concentrations.

Across six work packages, RECOMBINE-X will mine and structure over 70 years of pharmacokinetic and pharmacodynamic data into a unified database and use AI to prioritize the most promising drug combinations (WP1), simulate tumor-specific drug exposure through PBPK modelling (WP2), validate candidates in vitro and in vivo (WP3), translate the most promising therapies into two pediatric phase I/II clinical trials (WP4), and build a public, open-access PBPK/PD Explorer platform (WP5) so that the wider pediatric oncology community can query, compare and simulate drug exposure and effect data.

This position sits within Work Package 5, in which the Máxima, Medstone Science and Dr. Jan Koster build and govern the open-access PBPK/PD Explorer, in close integration with the established R2 platform at Amsterdam UMC. As the cloud/data engineer, you will build the bridge between this new pharmacology platform and our existing genomic and clinical data infrastructure at the Máxima, and help lay the technical foundation on which the wider consortium, and eventually the global pediatric oncology community, will be able to query, compare and simulate drug exposure and effect data for childhood cancer.