Data Scientist – Learning Science (New Grad) – Duolingo
Duolingo (NASDAQ: DUOL) is the world's most popular language learning platform with 100+ million monthly active users learning 40+ languages across 190+ countries. Duolingo's gamified app, powered by sophisticated learning science and adaptive algorithms, has become the most downloaded education app in the world and is helping more people learn languages than all the world's K-12 language teachers combined. Duolingo's Birdbrain ML platform personalizes every learner's experience — selecting the right lessons, scheduling spaced repetition reviews, and calibrating exercise difficulty to maximize learning outcomes. We are hiring New Grad Data Scientists in Pittsburgh to advance Duolingo's learning science and AI-driven personalization.
Responsibilities
- Conduct A/B experiments and causal inference analyses measuring the impact of Duolingo's pedagogical interventions on language learning outcomes and user retention
- Build learner performance models — using item response theory (IRT) and knowledge component models to estimate vocabulary acquisition, grammar mastery, and pronunciation proficiency
- Develop spaced repetition scheduling algorithms (SM-2, FSRS variants) optimizing the timing of vocabulary review sessions to maximize long-term retention across 100M+ active learners
- Analyze Duolingo's streak and gamification engagement data — building behavioral models of motivation, habit formation, and churn risk for Duolingo's retention team
- Build speech recognition accuracy models analyzing Duolingo's speaking exercise acceptance rates across languages, accents, and proficiency levels
- Develop Duolingo Max (GPT-4 powered) analytics — measuring AI tutor effectiveness, conversation quality, and learning outcome improvements for Duolingo's premium subscription
Requirements
- Bachelor's or Master's degree in Data Science, Statistics, Cognitive Science, or Educational Psychology
- Strong statistical skills — experimental design, causal inference, A/B testing, and Bayesian analysis
- Python proficiency for statistical analysis and ML model development
- Interest in learning science, psychometrics, or educational technology
- Familiarity with item response theory, spaced repetition, or adaptive learning systems is a strong plus
Benefits
- Competitive salary with Duolingo RSU equity and annual incentive
- Duolingo Super subscription for employees and family members
- Medical, dental, and vision benefits
- 401(k) with Duolingo matching
- Pittsburgh, PA headquarters — affordable, growing tech hub with Carnegie Mellon University proximity