Staff Data Scientist (Forecasting)

Join our team as a Staff Data Scientist (Forecasting) and be the technical lead for our forecasting team. You will own the strategy and implementation of forecasting models for key company metrics, lead the full modeling lifecycle, set the forecasting technical vision, translate forecasts into decisions, drive broader time-series impact, embed forecasting into the business, and lead and mentor a team of data scientists. The ideal candidate will have 8+ years of experience in building and shipping production time-series/forecasting models, excellent communication skills, a strong background in time-series modeling and applied statistics/econometrics, strong SQL skills, expertise in at least one scripting language, and a business acumen and ownership mindset.

- Be the technical lead for the forecasting team, owning the strategy and implementation of forecasting models. - Lead the full modeling lifecycle end to end, from problem framing to deployment, monitoring, and explainability. - Drive broader time-series impact beyond point forecasts, including anomaly detection and automated root-cause analysis.

- 8+ years of combined post-graduate academic and industry experience building and shipping production time‑series/forecasting models with web‑scale data - Proven technical leadership—success leading critical projects and materially influencing the scope and output of other contributors - A track record of delivering adjustable, well‑calibrated, and explainable forecasting systems that informing decision-making - Excellent communication skills—able to distill complex analyses and uncertainty into concise narratives for executive audiences - Strong background in time‑series modeling and applied statistics/econometrics; advanced degree (MS or PhD) preferred - Strong SQL skills (Hive/Presto/Spark SQL) and experience building reliable data pipelines/workflows (e.g., Airflow) - Expertise in at least one scripting language (ideally Python) - Business acumen and ownership mindset—able to simplify complex problems, connect model outputs to business levers, and prioritize for impact