Data Scientist

TL;DR

Data Scientist (Recommendations): Own metrics, experimentation, user behavior analysis, causal inference, and data foundations for personalized discovery in a fast-growing streaming platform with an accent on recommendation systems, A/B testing, and analytical rigor. Focus on building measurable frameworks, decoding engagement patterns across web/mobile/TV, distinguishing correlation from causation, and laying groundwork for custom ML models.

Provo, UT / Remote (Within US). Must be authorized to work in the United States. Travel required: 2-4 onsite events in Utah each year.

$110,000 - $130,000 a year

Company

Fast-growing entertainment distributor with a 10x expanding library of stories chosen by 2 million guild members, powering a unique streaming platform with theatrical-to-streaming pipeline.

What you will do

• Define, instrument, and maintain Discovery metrics framework (model, customer, business metrics) across web, mobile, TV.
• Own A/B testing pipeline using GrowthBook: design experiments with statistical rigor, sample sizing, guard-rails.
• Analyze user behavior: patterns in discovery, Guild voting, content affinity, churn risk across platforms.
• Apply causal inference to observational data: propensity matching, diff-in-diff, quasi-experiments.
• Build dbt models, data pipelines, analytical infrastructure for trustworthy data access organization-wide.
• Grow into feature engineering, model prototyping, and owning production models for recommendations.

Requirements

• 6+ years as data scientist or senior analytical role; experience with large-scale user engagement data (streaming/entertainment preferred).
• Statistical rigor: power analysis, confidence intervals, Bayesian methods; explain to non-technical stakeholders.
• Causal inference experience: propensity score matching, diff-in-diff, instrumental variables.
• SQL/Python fluency for exploration, analysis, modeling; clean, readable code.
• Experimentation: designed/analyzed production A/B tests, handle interaction/novelty effects.
• Data modeling with dbt or equivalent; familiarity with Snowflake/BigQuery, GrowthBook, BI tools.

Nice to have

• Recommendation systems/personalization experience.
• Python like software engineer: tests, packaging.
• ML lifecycle exposure: pipelines, feature stores, monitoring.

Culture & Benefits

• Hybrid work environment: private quiet area required; open shared office in Provo when onsite.
• Full-time 40 hours/week; comfortable air-conditioned office with assigned desks.
• Growth trajectory from data science to owning ML models in production, supported by team.
• Focus on analytical foundation first, then model building based on maturity.

Hiring process

• Standard interviews assessing statistical skills, causal inference, communication, experience.