Data Scientist II - Arcus Program

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Cloud computing, Scala Programming, Machine learning techniques, Data science techniques, MATLAB Programming, PyTorch, TensorFlow, R Programming

Job Description

We’re seeking breakthrough makers! Children’s Hospital of Philadelphia was built on the belief that we can change lives. Today, in every role throughout our hospital, research institute and care network, the 22,000 members of our workforce are finding new ways – big and small – to make a difference for the patients and families we serve.

If you are ready to challenge yourself, be inspired and grow – no matter what your role – you just may be the kind of breakthrough maker who will thrive at CHOP.

?CHOP is proud to share that we are ranked No. 1 on Forbes' 2022 list of America's Best Large Employers!

Job Summary

The Children’s Hospital of Philadelphia (CHOP) Research Institute’s “Arcus” program links large-scale clinical and biological data, providing services and tools for researchers to help solve the most challenging problems in child health. The Arcus team integrates with major scientific initiatives in lifespan, rare diseases, novel devices and therapeutics, precision health and continues to expand. We seek mission driven individuals with an interest in machine learning, statistics, software development, cloud computing and data privacy.

The tasks carried out by the Data Scientist II benefit health care researchers in a rapidly changing, fast-paced research setting. This will require the ability to learn and adapt quickly and collaborate with subject matter experts to develop novel frameworks and prototype solutions, while also expanding on supportable and maintainable software depending on project stage.

Work Site Expectation: This position is primarily remote but there is an opportunity to work onsite.

Job Responsibilities

The successful Data Scientist II candidate will have experience in software development (version control, design, testing), SQL, statistical knowledge, and machine learning. The day-to-day activities of the Data Scientist may include:

•  Implementing computational algorithms for testing and evaluation; interpreting data to assess and adjust algorithm performance.
• Developing high-quality code implementing machine learning models and statistical algorithms as application programming interfaces or other service-oriented software implementations.
• Participating in communication of research methods, implementation, and results to varied audience of clinicians, scientists, analysts, and programmers.
• Applying natural language processing (NLP) techniques to clinical text.
• Architecting container-based pipelines to process large-scale data.
• Applying spatial data analysis.
• Applying machine learning techniques to imaging and other clinical data.
• Customizing data annotation tools to enable researchers to annotate text and images.
• Deploying models to users within the Arcus platform by developing interactive tools and visualizations.
• Mentoring junior staff, student workers and co-ops.
• Communicating complex technical concepts to a lay audience.

Required Education and Experience

• Required Education: Bachelor’s Degree
• Required Experience: At least three (3) years of experience with progressively more complex data science, applied statistics, machine learning, or mathematical modeling projects.
• Preferred Education, Experience & Cert/Lic
• Preferred Education: Master’s in Analytics, Data Science, Statistics, Mathematics, Computer Science or a related field.
• Preferred Certificate in Analytics, Statistics, or Data Science.

Preferred Experience:

• At least four (4) years of experience with progressively more complex data science, applied statistics, machine learning, or mathematical modeling projects.
• Open-source machine learning platforms (TensorFlow, PyTorch)
• Working with sensitive data in a secure environment
• Natural language processing in the biological and medical domains
• Medical ontologies (SNOMED, UMLS, HPO)
• Kubernetes-based workflow engines
• Using SQL to perform filtering and aggregations within a data warehouse.
• Data manipulation libraries (pandas, data.table or dplyr).
• Spatial databases and Geographic Information Systems (GIS) services.
• Experience and demonstrated ability in acquiring new technical/analytic skills and domain knowledge to support successful contributions to research and development projects is preferred.
• Experience writing code in either applied educational or professional projects using one or more of the following languages: Python, Java or R is preferred.