Data Scientist (Alameda)

Key Responsibilities Design and productionize models for opportunity scanning, anomaly detection, and significant change detection across CRM, streaming, ecommerce, and social data. Define and tune alerting logic (thresholds, SLOs, precision/recall) to minimize noise while surfacing high-value marketing actions. Partner with marketing, product, and data engineering to operationalize insights into campaigns, playbooks, and automated workflows, with clear monitoring and experimentation. Required Qualifications Strong proficiency in

Python

(pandas, NumPy, scikit-learn; plus experience with PySpark or similar for large-scale data) and

SQL

on modern warehouses (e.g., BigQuery, Snowflake, Redshift). Hands-on experience with

time-series modeling

and

anomaly / changepoint / significant-movement detection (e.g., STL decomposition, EWMA/CUSUM, Bayesian/prophet-style models, isolation forests, robust statistics). Experience building and deploying

production ML pipelines

(batch and/or streaming), including feature engineering, model training, CI/CD, and monitoring for performance and data drift. Solid background in

statistics and experimentation : hypothesis testing, power analysis, A/B testing frameworks, uplift/propensity modeling, and basic causal inference techniques. Familiarity with

cloud platforms

(GCP/AWS/Azure), orchestration tools (e.g., Airflow/Prefect), and

dashboarding/visualization

tools to expose alerts and model outputs to business users.