Researcher, Prediction

What you'll do

• Own prediction research questions from hypothesis and data construction through evaluation, error analysis, and production handoff.
• Build and compare predictive methods, using temporal holdouts and prospective tests to assess calibration, robustness, and value beyond strong baselines.
• Communicate findings, uncertainty, limitations, and negative results through research notes and technical reports.

What they ask for

• Record of rigorous work in machine learning, forecasting, statistics, econometrics, quantitative research, decision science, or a related field.
• Experience building predictive systems from messy, heterogeneous data and evaluating them against observed outcomes.
• Strong research-code and empirical skills, including experiment design and detailed error analysis.
• Understanding of calibration and risks such as temporal leakage, selection effects, dataset shift, and subgroup imbalance.

Nice to have

• Experience in time-series modeling, econometrics, recommender systems, demand forecasting, risk modeling, causal inference, quantitative social science, or probabilistic programming.
• Experience with LLM agents, retrieval, tool use, post-training, synthetic environments, model-based reasoning, or inference-time scaling.

Tools

language models

AI focus

Develop and evaluate prediction systems that may combine language models, retrieval, tool use, quantitative models, inference-time reasoning, and simulated agents; determine whether these approaches add measurable predictive value.