Data Scientist

Job description

Data Scientist, Childhood Cancer Data Lab


CCDL Overview
Alex's Lemonade Stand Foundation (ALSF) is one of the leading funders of pediatric cancer research in the US and Canada. Since its inception in 2005, ALSF has funded more than 1,500 projects at nearly 150 institutions across the United States and Canada.
The Childhood Cancer Data Lab, an initiative of Alex's Lemonade Stand Foundation, was founded in August 2017 with the mission of empowering pediatric cancer experts poised for the next big discovery with the knowledge, data, and tools to reach it. The Data Lab is comprised of a team of software developers, data scientists and designers who are driven to build software systems, analytical workflows, and training programs in service of this mission. Members of the Data Lab simultaneously contribute to childhood cancer research and to the open science and open source software communities. We build in the open and collaboratively: examples of our work include the Single-cell Pediatric Cancer Atlas (ScPCA) Portal, OpenScPCA, and the Open Pediatric Brain Tumor Atlas (OpenPBTA). As the team grows, we are expanding our scientific capacity to support an international community of pediatric cancer researchers.
Position Overview, Duties and Responsibilities
The Data Scientist is a point person for data-intensive cancer biology within the Data Lab. The Data Lab science team activities include a mix of research (including collaborations), short-format training workshops, and processing and curation for data products utilized by the pediatric cancer community.
The Data Scientist is expected to identify opportunities to enhance Data Lab offerings and take a leadership role in execution. This team member will envision solutions that serve a community of dedicated scientists and clinicians, including those who receive grants from ALSF.
The Data Lab position will provide the Data Scientist with the opportunity to envision and enhance data-processing systems as well as systems that enable the user-guided analysis and interpretation of large-scale, multi-omic datasets. This member of the team will need an understanding of how to perform robust analyses of high-dimensional biological data and to integrate across data types. The role offers latitude that grows with experience and familiarity: greater independence on work that builds on a candidate's established expertise, and closer collaboration with the Data Science Manager and the rest of the team on newer or product-facing efforts. Working in the Data Lab also provides a unique opportunity to interact with the childhood cancer research community and its supporters at ALSF.
• Work with the Data Lab Data Science Manager to guide the biological challenges addressed by the Lab and/or to enhance Data Lab-led training efforts
• Perform and summarize analyses that seek to reveal new paths to treatment of childhood cancers or enhance Data Lab offerings, in collaboration with internal teams and external partners
• Integrate and harmonize across multiple data modalities (e.g., transcriptomic, genomic, epigenomic, proteomic, and imaging data) to address questions in pediatric cancer biology
• Work with the Engineering and Design teams to design systems that address pressing need in cancer biology
• Write and review clean, maintainable source code, documentation, and instructional material for public consumption
• Represent ALSF and the Data Lab at national conferences
All employees of the Foundation undertake other duties as needed and special projects as assigned. All positions at ALSF require occasional non-traditional work hours including evenings and weekends.
Work Location: Remote position; candidates must be available to work core hours aligned with Eastern Standard Time (EST). Candidates located within the greater Philadelphia metropolitan area are preferred.

Required Qualifications:
• PhD in Genetics, Genomics, Computer Science, Bioinformatics, or related field
• Expertise in the rigorous analysis of high-dimensional biological data (biological data science)
• Expertise in or the ability to transition to R or Python
• Excellent written communication skills
• Must be authorized to work in the U.S., no visa sponsorship available for this role
Preferred Qualifications:
• Demonstrable contributions to codebases for scientific projects
• A proven record of collaborative scientific research as evidenced by peer-reviewed publications or preprints
• An existing track record of cancer research
• Experience with workflow management systems (e.g., Nextflow)
• Cloud computing experience (e.g., Amazon Web Services)
• Experience developing or adapting instruction material
• Experience writing and reviewing analytical code in a collaborative environment
• Breadth across multiple data modalities is valued; experience working with single-cell or bulk transcriptomics, and/or integrating additional omics data types, is a plus
• Interest or experience in developing or applying machine learning and statistical methods for biological data

If interested, please submit your resume and cover letter describing your interest and why you are the right fit for the position. In the interest of expediting our process, only candidates who submit cover letters with resumes will be considered. Applications that include either a portfolio with work samples or demonstrable contributions to open source projects are preferred.