About this role
Role Overview
Advance AI-powered economic reasoning by designing rigorous evaluations for large language models and agentic systems. This remote, full-time research role combines economics, empirical analysis, and AI benchmarking to improve how models perform on complex economic research and policy workflows.
Key Responsibilities
- Design and refine evaluation frameworks for AI in economic domains, including benchmarks, scoring methods, and quality rubrics.
- Conduct research on economic reasoning and empirical analysis, translating findings into measurable AI performance improvements.
- Create datasets, test cases, and benchmark environments based on real-world economic research and policy challenges.
- Partner with researchers, economists, engineers, and product teams to evaluate and improve economics-focused AI models and agentic systems.
- Analyze model behavior and failure modes to identify research opportunities and improve performance.
- Apply econometrics, causal inference, and statistical analysis to assess AI capabilities on economic tasks.
- Produce technical reports, research findings, and best practices for AI evaluation in economics.
- Incorporate advances in AI, econometrics, and economic research into evaluation methodologies.
Qualifications
- PhD in Economics or a closely related quantitative field.
- 3 to 5 years of post-PhD applied economic research experience in industry, academia, or public policy.
- Expertise in at least one area such as labor economics, macroeconomics, industrial organization, productivity, technological change, or AI economics.
- Strong foundation in econometrics, applied microeconomics, and causal inference.
- Experience working with large datasets using SQL and statistical programming languages such as Python or R.
- Demonstrated empirical research or analytical-methodology development experience.
- Strong analytical, critical-thinking, problem-solving, written, and verbal communication skills.
- Experience producing research papers, technical reports, or policy briefs and collaborating with research, engineering, product, or policy teams.
Preferred Qualifications
- Experience developing or evaluating economics-focused AI, agentic workflows, or benchmarking environments.
- Familiarity with enterprise AI challenges and opportunities for economic research.
- Experience in cross-functional initiatives spanning economics, engineering, and product development.
Work Terms
- Remote, full-time position.
Compensation
- Listed annual compensation range: $400, 000 to $800, 000.
- National base-salary range: $200, 000 to $250, 000.
- Employees are eligible for equity compensation.