Senior Data Scientist

This is a fully remote position, open to applicants in United States.

📋 Description

• Identify and deliver predictive signals related to student engagement, outcomes, and partner health.

• Develop predictive models that seamlessly integrate with partners’ existing systems to drive actionable results.

• Establish actionable alert thresholds while considering the costs associated with false positives.

• Assess model performance across diverse student populations and document any limitations encountered.

• Continuously monitor deployed models for performance drift and retire those that no longer add value.

• Determine when analysis, definition changes, or discussions are more effective than creating a new model.

• Manage scheduling and oversight for models utilizing maintainable orchestration.

• Implement embeddings, clustering, and classification techniques on conversational, support, service, and other unstructured data.

• Translate insights from unstructured data into enhancements for product and partner experiences.

• Establish a foundation for text analysis that supports retrieval and AI tooling.

• Oversee the configuration of AI within the warehouse, including verified queries, prompts, agent tooling, and semantic views that showcase model outputs.

• Create and sustain an AI evaluation framework with detailed rubrics, sampling methodologies, and improvement reporting.

• Set evaluation standards and disseminate methodology to Product and Engineering teams.

• Provide internal teams with reusable data and analyses for strategic partners.

• Develop tools and training that empower teams to independently address inquiries.

• Record reasoning, assumptions, and trade-offs in the internal data knowledge base.

• Collaborate in dbt/code alongside engineers and contribute to shared definitions.

• Work together with Senior Data Engineer, Senior Analytics Engineer, Product, Engineering, Partner Success, Leadership, and external stakeholders.

⛳️ Requirements

• Over 5 years of experience in building predictive models that have been actively utilized.

• Several years of expertise in managing predictive modeling challenges, including calibration, threshold-setting, and feature leakage detection.

• Practical experience with NLP, encompassing text classification, clustering, embeddings, or similar applied tasks.

• Proficient in SQL.

• Working knowledge of Python for modeling and analysis purposes.

• Strong background in applied statistics.

• Experience with modern cloud warehouses such as Snowflake, BigQuery, Databricks, or related platforms.

• Familiarity with in-warehouse AI or agent tooling.

• Exceptional written and verbal communication skills.

• Ability to navigate ambiguity and a willingness to acknowledge uncertainty.

• Experience with version control and code review processes.

• Proven experience in productionizing model outputs into operational workflows.

• Background in scheduling and monitoring recurring production jobs.

• History of prioritizing ambiguous business objectives into well-defined projects.

• Willingness to assess model performance across student populations and document limitations.

• Nice to have: Experience with dbt or similar transformation tools, dimensional modeling, or analytics engineering.

• Nice to have: Familiarity with AI evaluations or prompt evaluations.

• Nice to have: Experience with BI tools such as Sigma, Looker, Hex, Tableau, or similar.

• Nice to have: Collaborative experience with analytics or data engineers.

• Nice to have: Background in linguistics or computational linguistics.

• Nice to have: Experience in EdTech, higher education, or student success initiatives.

🏝️ Benefits

• A collaborative and inclusive work environment.

• Opportunities for personal and professional growth.

• Promotion-from-within career opportunities.

• Support and mentorship focused on long-term success.

• Primarily remote work arrangement.