Job descriptionWe’re seeking Statisticians with strong English writing skills to join our Deep Research for Forecasting project. In this role, you will review time-series plots (a quantity of interest over time) along with brief contextual descriptions, then identify the most meaningful patterns in the data and produce concise, well-reasoned causal chains explaining what likely drove those patterns. Your work will help create high-quality tasks used to train and evaluate AI systems on forecasting-related reasoning. You will focus on distinguishing signal from noise, articulating plausible mechanisms (root cause → intermediate drivers → observed time-series impact), and writing explanations that are clear, grounded, and useful for downstream model training. Key Responsibilities: • Create Forecasting Training Tasks: Given a time-series plot and short description, identify the most important patterns (trend, seasonality, regime changes, outliers, step changes, cyclical behavior, variance shifts) and document them clearly. • Write Causal Chains: Produce concise causal narratives that explain patterns from root cause → mechanism → observable time-series effect, prioritizing the most meaningful drivers and avoiding generic explanations. • Ensure Clarity & Usefulness for AI Training: Write structured, high-signal explanations that are easy to evaluate, minimizing ambiguity and making assumptions explicit when necessary. • Maintain Consistency & Quality: Follow project guidelines and rubrics to ensure outputs are accurate, coherent, and comparable across many examples. • Weekly Commitment: 10 hours/week Your Profile: • You have an educational and/or professional background in Statistics or a closely related field (e.g., Mathematics, Data Science). • Proficient in time-series analysis and forecasting (e.g., trend/seasonality, structural breaks, anomalies, volatility shifts, lag effects). • Excellent English writing skills with a clear, structured, concise style. • Strong analytical judgment and ability to interpret data visualizations with precision. • Comfortable forming plausible causal explanations while clearly separating evidence from assumptions. • Optional: Domain knowledge in one or more of the following: Healthcare; Climate/oceanography; Economics & finance; Cloud operations; Transportation.
