Data Scientist II/III

Title: Data Scientist II/III Duration: 12 months (Extendable) Location: West Point, PA 19486 (Hybrid) Required to be onsite for at least 2–3 days per week at the West Point, PA site Department Information / Introduction • Establishing data workflows for predictive tools to enable more effective identification, characterization, and development of medicines and vaccines is a key objective • This position sits within the Digital Sciences team in the Analytical Enabling Capabilities sub-department of Analytical Research & Development • You will be part of a team working collaboratively across a wide range of areas impacting all aspects of the drug discovery and development pipeline • A diverse array of projects spanning data workflows to instrument metrology to predictive sciences ensure this Digital Sciences team helps to enable work across all drug modalities including small molecule, peptide, biologics, vaccines, and beyond • The core Digital Sciences team works with a networked group of digital champions across AR&D and has close connectivity to other digital/data facing teams including critical IT collaborators Responsibilities / Day-to-Day • Design and development of data workflows/data pipelines in Python • Meet with business clients/SMEs to gather requirements • Work with IT to implement data workflows • Manage projects and timelines • Estimation of duration of work • Participate in daily standup meetings • Presentation of updates to collaborators Education: • Degree in computer science or related field; or a degree in the chemistry disciplines with strong programming capabilities Experience • 7–8 years of relevant experience Must Have / Required Skills • Cloud Services – AWS (Lambda Functions, S3, Cloud Formation Templates, RDS, ECR) • Development of ETL Processes / Data Workflows / Data Pipelines / Data Wrangling / Data Ingestion • Python 3.9+ software development • Python packages – Boto3, Pandas, pyodbc, openpyxl • Python virtual environments – conda • IDEs – Visual Studio Code or PyCharm • Software design, development, and testing (unit testing and system testing) • Version control – Git, GitHub • CI/CD – GitHub Actions • Databases – relational databases, SQL, data modeling and design • File formats (XLSX, YAML, JSON, CSV, TSV) • Excellent verbal and written communication skills • Ability to work independently and collaborate as a team • Strive for continuous improvement and suggest innovative solutions to scientists' common challenges related to data workflows Nice to Have / Preferred Skills • Cloud Services – AWS (SQS, DLQ, SNS, EventBridge, API Gateway) • Development of ETL Processes / Data Workflows / Data Pipelines / Data Wrangling / Data Ingestion • Python packages (Cerberus, PyYAML, logging) • Python linters and type hints; regular expressions • Experience with data pipeline tools such as Dataiku or Trifacta • Experience in an IT role within the pharmaceutical research sector Notes • This is not a typical IT role • Someone who can work with scientists to understand what data has been generated from experiments and help automate the Electronic Notebook • Someone who has expertise generating scientific data, can be analytical, genomics • • Someone who has expertise building data pipelines