Prediction Researcher

Aaru
New York
Workplace: OnsiteFull timeFunction: Research & Scientific (R&D)Skills: ["Intellectual honesty","Rapid learning","Clear communication"]

Own difficult prediction problems about aggregate human behavior and future outcomes. Build and evaluate calibrated forecasting methods using heterogeneous real-world data, combining probabilistic modeling, structured data, retrieval, language models, and agent simulation when it adds measurable signal. Design holdouts and prospective tests, diagnose failures across subgroups and time, and hand reproducible methods to engineering while communicating results clearly, including null or unstable outcomes.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Aaru
Aaru
3 days ago

Prediction Researcher

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 13 hours agoStatus: Live

Job Summary

Own difficult prediction problems about aggregate human behavior and future outcomes. Build and evaluate calibrated forecasting methods using heterogeneous real-world data, combining probabilistic modeling, structured data, retrieval, language models, and agent simulation when it adds measurable signal. Design holdouts and prospective tests, diagnose failures across subgroups and time, and hand reproducible methods to engineering while communicating results clearly, including null or unstable outcomes.
Location: New York
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)

Key Responsibilities

  • •Own a high-value prediction problem, turning ambiguous questions into falsifiable hypotheses with explicit success criteria.
  • •Construct or curate datasets and build predictive methods from real-world records, including transactions, usage, event histories, and longitudinal outcomes.
  • •Design temporal holdouts and prospective tests using only information available at prediction time, and measure calibration, scoring, and robustness.
  • •Compare complex approaches against strong baselines and diagnose errors by population, subgroup, time period, and confidence level.
  • •Hand validated methods to engineering as reproducible systems with documented assumptions, limits, and failure modes, and write clear research notes and reports.

Key Requirements

  • •Rigorous experience 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 understanding of calibration and why accuracy alone is insufficient for consequential prediction.
  • •Ability to design honest evaluations that address temporal leakage, selection effects, dataset shift, and subgroup imbalance.
  • •Comfort moving between data construction, model design, implementation, experiment design, and detailed error analysis.
Experience:Machine learningForecastingEconometricsQuantitative research
Skills:Intellectual honestyRapid learningClear communication
Tech Stack:Machine learningForecastingStatisticsEconometricsProbabilistic modelingLanguage modelsRetrievalTool useAgent simulationTime-series modelingCausal inferenceProbabilistic programming

Company Brief

Aaru
Aaru builds multi-agent simulation software that models entire populations to predict behavior and future events, replacing traditional research with decision-ready forecasts for enterprises, governments, and agencies across industries.
Industry: AI & Machine Learning
Company Size: Small (11 to 50 employees)
Revenue: USD 1M to 5M
Growth: Early Stage Startup
Valuation: Unicorn (USD 1B+)
Funding: Series A
Headquarters: San Francisco, United States
Founded: 2024
WebsiteLinkedIn