Senior Data Scientist

LEMNIS

Senior Data Scientist building predictive models and NLP tools for Mainstay, whose platform helps colleges and businesses drive actionable conversations. Owning AI evaluation, data tooling, and production model monitoring.

Posted 9/10/2026full-timeRemote • 🇺🇸 United StatesSenior💰 $150,000 - $165,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and evaluating predictive models, particularly in the context of student engagement and outcomes. Proficient in applying natural language processing techniques and managing data workflows within modern cloud environments.

Highest-signal resume keywords

Predictive ModelingNatural Language Processing (NLP)SQLPythonCloud Data Warehousing

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Predictive ModelingText ClassificationClusteringEmbeddingsApplied StatisticsSQLPythonModel CalibrationFeature Leakage DetectionProductionizing Model Output

Soft Skills

Excellent Written CommunicationExcellent Verbal CommunicationComfort with Ambiguity

Tools & Technologies

SnowflakeBigQueryDatabricksDbtSigmaLookerHexTableau

Industry Keywords

EdTechHigher EducationStudent SuccessAI ToolingAnalytics Engineering

Tech Stack

Tools & technologies

BigQueryCloudPythonSQLTableau

About the role

Key responsibilities & impact

Find and ship predictive signals across student engagement, outcomes, and partner health
Build predictive models that integrate with partners’ existing systems and drive action
Set actionable alert thresholds and account for false-positive costs
Evaluate model performance across student populations and document limitations
Monitor deployed models for drift and retire models that no longer provide value
Decide when an analysis, definition change, or conversation is preferable to building a model
Own scheduling and monitoring for models using maintainable orchestration
Apply embeddings, clustering, and classification to conversational, support, service, and other unstructured data
Turn unstructured-data findings into product and partner-experience improvements
Build text-analysis foundations for retrieval and AI tooling
Own in-warehouse AI configuration, verified queries, prompts, agent tooling, and semantic views exposing model output
Build and maintain an AI evaluation framework with precise rubrics, sampling methodology, and improvement reporting
Set evaluation standards and share methodology with Product and Engineering
Equip internal teams with reusable data and analysis for strategic partners
Build tooling and training that enable teams to answer questions independently
Document reasoning, assumptions, and tradeoffs in the internal data knowledge base
Work in dbt/code alongside engineers and contribute to shared definitions
Collaborate with Senior Data Engineer, Senior Analytics Engineer, Product, Engineering, Partner Success, Leadership, and external stakeholders

Requirements

What you’ll need

5+ years building predictive models that someone actually used
Several years owning predictive modeling problems, including calibration, threshold-setting, and detecting feature leakage
Practical NLP experience, including text classification, clustering, embeddings, or similar applied work
Strong SQL skills
Working Python skills for modeling and analysis
Solid applied statistics
Experience with a modern cloud warehouse such as Snowflake, BigQuery, Databricks, or similar
Experience with in-warehouse AI or agent tooling
Excellent written and verbal communication
Comfort with ambiguity and honesty about uncertainty
Experience working in version control with code review
Experience productionizing model output into an operational workflow
Experience scheduling and monitoring recurring production jobs
Track record of prioritizing ambiguous business goals into scoped projects
Willingness to evaluate model performance across student populations and document limitations
Nice to have: dbt or similar transformation tooling, dimensional modeling, or analytics engineering exposure
Nice to have: AI evaluations or prompt evaluation familiarity
Nice to have: Sigma, Looker, Hex, Tableau, or similar BI tool experience
Nice to have: Experience working closely with analytics or data engineers
Nice to have: Linguistics or computational linguistics background
Nice to have: EdTech, higher education, or student success background

Benefits

Comp & perks

Collaborative and inclusive work environment
Personal and professional growth opportunities
Promotion-from-within opportunities
Support and mentorship aimed at long-term success
Primarily remote work arrangement