Data Scientist I Jobs

The laboratory of Dr. Christopher Topp at the Donald Danforth Plant Science Center is a plant root phenomics lab, innovating uses of 3D imaging modalities to investigate roots and their environment. We are seeking someone interested in plant biology and data analysis to help process and measure digitized plant samples using both external and internal analysis tools. Many of our projects involve high-throughput phenotyping. As such, a desirable candidate would be capable of writing reusable, efficient, and well-commented code. The successful candidate will be organized, independent, creative, have strong communication skills, desire to learn, and work with outstanding collaborative capability.

Much of the data in our lab are 3D reconstructed volumes from our large-format X-ray Tomography (XRT) system and X-ray microscope (XRM) system, but we handle a variety of other types of data depending on the project (e.g. genomics data, PET images, hyperspectral images). Given the size and variety of data in the lab, this job involves maintaining a robust computational infrastructure–including dedicated workstations, storage and processing servers, virtual machines, internal code bases, third-party software licenses, VR systems, databases, and data management. The role allows for creativity and autonomy in the design and development of tools and procedures.

Responsibilities:

• Uses knowledge of statistics, machine learning, image segmentation, and computer science to develop analysis pipelines and perform “one-off” analyses on existing datasets.
• Works closely with another data scientist and other lab members to enhance existing processes
• Manages research data and storage media (e.g., files, database, documentation making up 500+ TiB)
• Occasionally helps with data collections from agronomic fields, greenhouses, and wet lab
• Provides support for research software tools (e.g., write SOPs, perform updates, troubleshooting)
• Trains lab members on how to use pipelines and related tools
• Maintains and provides support for workstations (Windows, Debian/Ubuntu) and servers (CentOS)

Required knowledge, skills, and abilities:

• Willingness to learn/use a variety of programming languages depending on the needs of a project
• Strong Interest in Plant Science and Agriculture
• Strong problem solving and critical thinking skills
• Effective communication skills and ability to produce high-quality oral and written research products
• Strong proficiency with Python and its ecosystem, including data science and scientific computing
• Familiar with version control systems (Git) and GitHub
• Able to organize their time efficiently and work both independently and collaboratively within a multidisciplinary and interactive research environment
• Goal-oriented, creative individual who thrives in a dynamic and collaborative environment

Preferred knowledge, skills, and abilities:

• Strong competency in scientific computing for both development (C++, Matlab, Python) and specialized third-party tools (e.g., samtools)
• Able to quickly learn new libraries, frameworks, and tools
• Familiar with any of the following languages: C, C++, Python2/3, Matlab, R, Shell, Java, Make, SQL
• Experience in Plant Science
• Excellent documentation skills and use of self-documenting code
• Comfortability working with custom file formats, both binary and plain text formats
• Understanding or exposure to Linux operating systems and familiarity with tools used to manage packages (dnf/yum/apt), compiling from source (i.e., Makefile), and routine system maintenance and troubleshooting
• Experience with data management and its best practices for dealing with both large files (40+ GiB) and numerous files (800,000+) per dataset
• Familiar with image segmentation and image analysis concepts
• Comfortable with packaging and distribution (Python/PyPI, Matlab, R/CRAN, Debian/RHEL, or similar)
• Understanding of computer components and how they interact

Education Qualifications:

• B.S. or M.S. in Computer Science, Data Science, or similar degree

Submission:

• CV
• Cover Letter
• Contact information for three (3) professional references

About the Donald Danforth Plant Science Center:

Founded in 1998, The Donald Danforth Plant Science Center is an independent, non-profit organization with a mission to improve the human condition through plant science. Our focus is scientific research at the nexus of food, energy and the environment to improve the productivity and sustainability of agriculture. We assemble interactive teams of scientists and develop unique platforms to discover underlying principles about how plants work. We then convert that knowledge into useful crops and products, and partner with organizations that are best positioned to solve problems where they exist around the world. The Center’s work is funded through competitive grants from many sources, including the National Institutes of Health, U.S. Department of Energy, National Science Foundation and the Bill & Melinda Gates Foundation and charitable contributions from individuals, companies, and foundations.

The Donald Danforth Plant Science Center is proudly an equal employment opportunity employer. Employment decisions at the Danforth Center are based on merit, qualifications, and abilities. It is our policy that the Danforth Center does not discriminate in employment opportunities on the basis of race, color, religion, sex, sexual orientation, gender identity, age, or national origin and status as protected veterans or individuals with disabilities. If you need a reasonable accommodation to access the information provided on this web site, please contact Human Resources, at 314-587-1033, for further assistance.