Sr. Data Scientist

Quizlet•San Franciso, CA

1d•Hybrid

About The Position

Quizlet’s Content Platform & Experience team owns how learning content is created, found, and studied, spanning user-generated study material and its quality and safety, search, creation, and conversational AI experiences. The team partners closely with the Data Platform and product teams. The Data Scientist will build trust in the team’s data and enable partners to answer most questions independently. The role ensures content, search, and Coach data reaches the data store correctly; defines key metrics; supports high-stakes experiments and search and recommendation evaluation; and measures how well AI Coach helps learners. Approximately 30% of the role focuses on data engineering, including optimizing and ensuring the reliability of the search data pipeline.

Requirements

At least 4 years of experience in data science or product analytics.
A degree in statistics, computer science, economics, math, or another quantitative field.
Advanced SQL and proficiency in Python.
Hands-on experience designing and analyzing A/B tests, with solid statistics knowledge including hypothesis testing, regression, and causal inference basics.
Hands-on data modeling in a warehouse, such as dbt on BigQuery, including data contract tests.
Working knowledge of batch pipelines such as Airflow, including incremental loads, backfills, and the order in which changes must ship.
Experience owning data quality for a product area, including event instrumentation, tracking plans, and validation.
Experience building training or evaluation datasets from product logs.
A track record of helping non-technical partners self-serve data through training, documentation, or well-designed dashboards.
Clear written and verbal communication.

Nice To Haves

Experience with Omni, Looker, or another BI semantic layer.
Recommender evaluation experience, such as recall or NDCG, or experience with feature stores such as Feast.
LLM or conversational AI evaluation experience, such as Arize.

Responsibilities

Own the data quality used to measure domain health and iterate on experiments.
Write tracking plans and data contracts for new features so launches have trusted usage data from day one.
Define engagement metrics for content health, search quality, and conversational experiences, and make them available in Omni dashboards used by teams every week.
Design and analyze high-stakes A/B tests across search ranking, AI feature rollouts, and content features.
Own dbt models and contract tests that feed search indexes.
Build reproducible training and offline-evaluation datasets for search ranking and recommendation models.
Optimize and ensure the reliability of the search data pipeline.