Position Overview
As a Data Science Intern for the PSTO function, you will play a crucial role in integrating and streamlining test results from various development and manufacturing processes, including characterization, design verification test, process control tests, manufacturing lot release tests, and stability data. Your primary focus will be on developing systems that automatically aggregate and centralize these datasets from different storage locations (e.g., Astria and/or partner SharePoint, software platforms, cloud storage) This may involve proposing and working with internal and external data owners to align on optimal formats of the data.
Also, you will be responsible for designing an interface that allows users to easily access, compare, and analyze various development and manufacturing test data. Use of artificial intelligence tools is desirable to make the processes as simple as possible, and extendable for the future. As a stretch goal, a similar process can be applied to not only data but also documentation, i.e. create an automatic digital project history file or design history file.
Responsibilities
Data Pipeline Development and Integration
- Identify and map out existing sources of test results, including SharePoint sites, software systems, and external databases.
- Develop and implement a data pipeline framework to automatically centralize test results in a single cloud-based repository.
- Collaborate cross-functionally with the IT and PSTO teams to ensure proper data extraction and integration from various platforms.
User Interface Development
- Design and create a user-friendly dashboard that displays key test results for analysis and comparison for the PSTO team.
- Ensure that the interface provides lot-to-lot comparisons, highlights out of specification results, and allows users to track trends over time.
- Enable access to test method information to ensure transparency in data interpretation.
Ensure Compliance of the Platform
- Work closely with the Quality and Regulatory teams to ensure the accuracy, completeness, and regulatory compliance of the integrated datasets.
- Assist in creating documentation for data pipeline processes and system functionalities.
Collaboration and Communication
- Engage with key stakeholders on cross-functional teams to gather relevant input and ensure alignment on PSTO initiatives.
- Communicate effectively with team members, sharing insights, progress, and challenges in a clear and concise manner.
- Deliver a final presentation at the end of the internship summarizing findings, demonstrating the developed interface, and proposing recommendations for future improvements.
Qualifications
- Currently pursuing a degree in Engineering, Data Science, Computer Science, Life Sciences, or a related field.
- Strong analytical skills with a keen interest in data integration and visualization.
- Experience or coursework in Python, SQL, Power BI, Tableau, or other data analytics tools is preferred but not required.
- Proficient in Microsoft Office Suite.
- Excellent communication and interpersonal skills, with the ability to work cross-functionally.
Astria’s Commitment
At Astria, we are committed to building a diverse team where every Astrian endorses the idea that people bring their authentic self to work. We embrace a patient-first, people-always culture which strives to ensure all Astrians and our collaborators have a sense of belonging and receive the support they need to thrive. We invest in our people through our words, our actions, and our values. We are working to develop and implement initiatives that promote diversity, equity, and inclusion throughout the organization and foster a culture of openness, respect, and collaboration, where all voices are heard, and everyone is valued for their unique perspectives and contributions.
People are our greatest asset, and only with a diverse team can Astria shine brighter. Together we can bring our passion and compassion to the work of delivering life-changing therapies to patients, families, and communities.