Research Scientist

Effectief Altruisme; United States; Remote; USD 120,000 - 160,000; Full time

Job summary

Effectief Altruisme is seeking a research scientist to lead AI capability discovery through long-horizon agent experiments and data analysis. You will design and run experiments using AI Village infrastructure to test hypotheses about frontier AI agent behavior and capabilities.

You will analyze more than a year of Village data to surface insights about emergent dynamics, long-horizon reasoning, and model proclivities, contributing to assessments of risk and policy relevance for researchers and

Qualifications

• Strong LLM research background and ability to identify important questions.
• Experience analyzing long-horizon data and emergent dynamics.
• Ability to analyze multi-year Village data to surface insights on emergent dynamics and long-horizon reasoning.
• Strong background in LLM research and rigorous analytical methods.

Responsibilities

• Design and run experiments to test hypotheses about frontier AI agent behaviour and capabilities.
• Analyze over one year of Village data to surface insights for researchers and policymakers.
• Collaborate with researchers to assess risks of powerful AI.
• Conduct rigorous LLM research and analyses.

Skills

LLM research

Data analysis

Experiment design

Tools

AI Village infrastructure

Job description

Research scientist leading AI capability discovery through long-horizon agent experiments and data analysis.

• Design and execute experiments using AI Village infrastructure to test hypotheses about frontier AI agent behaviour and capabilities.
• Analyze >1 year of Village data to surface insights about emergent dynamics, long-horizon reasoning, and model proclivities.
• Strong LLM research background with excellent taste for identifying important questions and executing rigorous analyses.

De meeste tests van AI meten wat een model in één korte taak doet. AI Digest laat AI-agenten al meer dan een jaar samen aan langlopende opdrachten werken, en wat jij uit die zeldzame gegevens haalt, komt terecht bij onderzoekers en beleidsmakers die moeten inschatten hoe groot de risico's van krachtige AI echt zijn.