Core Responsibilities

The staff scientist (informatics algorithms engineer) position will focus on Translational Data Analytics. The selected candidate will develop custom workflows and novel methods to handle translational research data and will deploy and maintain related tools internally and publicly.

The successful candidate will develop novel artificial intelligence (AI), deep learning (DL) and machine learning (ML) methods. They also will design a robust computational framework that allows access to and interpretation of translational research data. This framework will involve data parser and analytics development for NCATS-generated and public data, knowledge source and database (relational and graph) maintenance and development, API access, interactive visualization, and more. This framework will be largely publicly available to the broader research community.

The selected candidate will interact closely with the IFX Core Director, computational and noncomputational IFX Core and NCATS scientists (e.g., biologists, chemists, clinicians), and our academic collaborators. They will contribute to the strategic vision and mentoring of trainees and staff. The selected candidate will be encouraged to seek NCATS, NIH or external collaborations to further disseminate our data, methods and software. The candidate will help aggregate and clean in-house translational research data (e.g., high-throughput screens; multi-omic; knowledge sources on chemical, biological or disease annotations). They also will leverage these data in collaborative translational research projects. To support translational research efforts, the selected candidate will be part of a broader effort to standardize chemical, biological, disease and clinical annotations and promote the integration of these related lines of information.

NCATS expects the selected candidate to create and maintain detailed documentation on all work products to facilitate reuse and collaboration with IFX members, other researchers and DevOps. The candidate will contribute to and follow best practices in software and application development, including producing clean code and architecture. They also will be an owner/point of contact for the computational framework and its individual components. They generally will make the tools easier to maintain and make them more modular through appropriate containerization (e.g., Docker).

The selected candidate, with DPI staff, will help build a consolidated scientific computing environment, integrating libraries and software and ensuring they are interoperable. They also will apply or develop appropriate, state-of-the art methods to support large-scale data-acquisition efforts within DPI. The position requires the selected candidate to actively participate in IFX Core and NCATS committees and meetings and, as appropriate, showcase and collect feedback (e.g., user feedback) on the framework. Participation will include best practices for team development, such as design review and peer code review. The selected candidate will draft manuscripts and publish results in high-impact, peer-reviewed scientific journals and present results at internal and external scientific meetings.