Research Scientist, Agent Evaluation and Market Mechanisms

• Design simulated auctions, negotiations and markets with induced values, so the efficient outcome is known for every run.
• Run LLM agents from many model families in these markets, and log every bid, message and stated reason.
• Measure efficiency, price convergence, biases and collusion, and test which measures stay stable across repeated runs.
• Test whether a mechanism's incentives hold when agents bid, such as truthful bidding in second-price auctions.
• Compare agent behavior with published results from experiments with human subjects.
• Write down hypotheses before the runs start, and report results with the run logs behind them.
• Publish research papers, and write reports for clients on what the agents did and why.

• A PhD in economics, computer science, operations research or a related field, or equivalent research experience.
• Research experience in mechanism design, auction theory, game theory or experimental economics.
• Experience running experiments with LLMs or LLM agents.
• Python for simulation and analysis.
• A record of publications or other written research.

• Experience with multi-agent reinforcement learning or agent-based models.
• Experience running laboratory experiments with human subjects.
• Knowledge of market microstructure.

$130,000 to $201,000 a year

Full-time W-2 employment with health insurance, a retirement plan and paid leave.

No application deadline. We accept applications for this role on an ongoing basis.

Remote, United States