Sr Data Scientist

Ascend Learning, LLC•Leawood, OR

1d•Remote

About The Position

Ascend Learning, a leading healthcare and learning technology company, is the connection between a powerful portfolio of brands serving students, educators, and employers with outcomes-based, data-driven solutions across the lifecycle of learning. From testing to certification, Ascend Learning products are used by physicians, emergency medical professionals, nurses, allied health professionals, certified personal trainers, financial advisors, skilled trades professionals and insurance brokers. Headquartered in Burlington, MA, with additional office locations and hybrid and remote workers in cities across the U.S., Ascend Learning was recognized by Newsweek and Plant-A Insights Group as one of America’s 2025 Greatest Workplaces as well as America’s Best Places to work for Mental Well-Being for 2025. We're always looking for talented, passionate professionals to join us in our mission to help change lives. If this sounds like an environment where you'd thrive, read on to learn more.

Requirements

Bachelor’s degree in Data Science, Statistics, Applied Mathematics, Computer Science, Educational Measurement, or a closely related quantitative field.
5+ years of experience in data analysis or data science with demonstrated progression in technical scope and complexity
Expert-level SQL across both Snowflake and SQL Server — stored procedures, query optimization, and complex multi-source joins
Proven experience building statistical models and applying machine learning techniques such as classification, clustering, and anomaly detection in a production or near-production context
Proficiency in Python, R, Snowflake ML for statistical analysis and model development
Experience building and publishing Tableau dashboards for operational and executive audiences
Demonstrated ability to communicate complex findings clearly and persuasively to non-technical stakeholders, including senior leadership
Strong business acumen with the ability to prioritize analytical work by impact and translate ambiguous questions into structured analytical frameworks
Proven experience working cross-functionally with engineering, product, and IT teams and engaging with vendor technologies

Nice To Haves

Master’s degree preferred in a quantitative discipline
familiarity with psychometric methods
experience with remote proctoring platforms
exposure to Medallion/EDW architectures in Snowflake
background in test security, fraud detection, or behavioral analytics at scale

Responsibilities

Design and implement statistical models, anomaly detection algorithms, and machine learning pipelines to identify suspicious test-taking patterns, proxy testing, impersonation, and item exposure across large-scale assessment datasets.
Build and maintain predictive and classification models — including logistic regression, clustering, random forest, and NLP-based flagging — to surface security risks and prioritize investigation queues.
Independently prepare and present findings, dashboards, and security briefings to senior leadership — translating complex analytical outputs into clear, actionable narratives.
Author detailed analytical reports supporting security investigations, including methodology documentation, evidence summaries, and recommended actions.
Write and maintain complex Snowflake SQL and T-SQL — stored procedures, views, and optimized queries — across Snowflake and SQL Server environments, integrating data from disparate sources including NoSQL, data lakes, APIs, and external data providers; contributing to EDW Gold layer development for exam security use cases.
Design, build, and maintain Tableau dashboards that surface key security metrics, incident trends, and performance indicators for both operational teams and senior leadership.
Partner with Psychometricians, Data Engineering, IT security, and remote proctoring vendors to align on analytical requirements, data quality standards, and the technology landscape — ensuring security data is accurate, timely, and fit for analysis.
Convert ambiguous needs from Test Security, IT, Legal, and Operations into well-defined analytical requirements and data specifications, maintaining clear documentation of models and methodologies throughout.