Job Summary

The Data Science team is responsible for building out the machine learning capabilities of Imprivata's Digital Identity Platform, with specific projects ranging from detecting patient privacy violations to using machine learning to empower what would be otherwise manual workflows.  As a Sr. Data Scientist, you'll be deeply involved in every aspect of the project lifecycle, including gathering requirements, cleaning and exploring datasets, running machine learning experiments, and deploying services to production.

Duties and Responsibilities

As a Sr. Data Scientist, you'll be expected to: 

• Put ethics and security first.  The datasets that we use almost invariably contain PHI or similarly sensitive information, and we take the responsibility that comes with that access seriously. 
• Drive business value with machine learning.  That includes everything from initial framing of the problem, to pulling and working with data, to training models, to communicating results. 
• Write high quality, production Python code.  While we work closely with other engineering teams, we don't hand off research code to be productionized by someone else -- we own our solutions end-to-end and do our best to keep raising the technical bar. 
• Build a breadth of machine learning knowledge.  Beyond actually training models, you'll rely on that fluency when it comes to tasks like gathering requirements or iterating on model output with subject matter experts. 
• Communicate effectively.  Taking your project from business problem to production service isn't a solo exercise; you'll need to work well with people from other teams and our own in order to succeed. 
• Improve the team.  Everyone is responsible for making the team better: as a Sr. Data Scientist, you'll have an informal mentorship role by way of things like pair programming and providing meaningful code reviews. 

Qualifications

• Excellent problem solving skills. 
• Solid experience with Python and common Data Science packages, such as NumPy, pandas, and scikit-learn.  Additional experience with relevant packages such as PyTorch, Dask, Pydantic a plus. 
• Strong understanding of standard machine learning techniques such as classification, regression, clustering, dimensionality reduction.  Additional expertise in specific areas such as NLP, anomaly detection, graph methods, etc. a plus. 
• Proficiency with SQL and relational databases. 
• Experience working in a Unix environment. 
• 2-5 years of data science experience. 

 #LI-Hybrid #LI-LI1