Researcher

Aaru operates at the frontier of predictive intelligence, using AI to simulate and predict human behavior at scale. By generating and deploying instances of artificial intelligence that mirror humans, called agents, Aaru simulates entire populations with unprecedented accuracy. Our partners work with us for many reasons: they leverage Aaru to refine strategy in volatile geopolitical climates, cut new product innovation timelines from months to minutes, and deploy marketing campaigns that win in an era where consumers have never been harder to understand. We provide organizations with invaluable foresight, empowering them to anticipate outcomes and proactively make the right decisions at the right time, every time.

We're a small, dedicated, mission-driven team and we intend to stay that way. We believe the best work happens when exceptionally talented people are given ownership, trust and the space to operate without bureaucratic friction. We work with urgency and intellectual honesty and expect new team members to match our velocity. We seek individuals who thrive at the frontier, who push beyond conventional limits, who bring curiosity and conviction in equal measure, and who want their work to have demonstrable impact in the world. If you're energized by the idea of a small team doing things that feel impossible, let’s build together.

As a Researcher at Aaru, you will design, build, and improve the simulation systems that generate high-fidelity synthetic agents from real-world profiles. The Research team is responsible for Aaru's core simulation capabilities — the technology that enables our customers to test decisions against realistic populations before committing to them.

• →

  Design and advance methods for synthesizing realistic agents from structured and unstructured profile data

• →

  Build and evaluate simulation pipelines that produce population-level distributional accuracy across demographic, attitudinal, and behavioral dimensions

• →

  Develop techniques for grounding agent behavior in real-world data sources — surveys, behavioral traces, psychometric instruments, and domain-specific datasets

• →

  Design hybrid architectures that combine large language models with classical methods from computational social science, psychometrics, and survey methodology

• →

  Build rigorous evaluation frameworks that measure simulation quality against known ground-truth distributions (e.g., GSS, census, proprietary panel data)

• →

  Identify and close gaps between simulated and observed population behavior through iterative experimentation

• You have deep experience with synthetic data generation, agent-based modeling, computational social science, or population simulation

• You are interested in using LLMs as a simulation substrate — not just for text generation, but for producing structured behavioral outputs that hold up under statistical scrutiny

• You think carefully about what it means for a simulation to be "accurate" and can articulate the difference between individual-level plausibility and distributional fidelity

• You have a PhD in ML, computational social science, cognitive science, statistics, psychometrics, or a quantitative field — or equivalent depth from industry research

• You communicate clearly about what's working and what isn't, including when results are null or ambiguous

• You move fast and are comfortable producing work at high velocity without sacrificing rigor

• Have built systems that generate or evaluate synthetic populations at scale

• Have experience with survey methodology, psychometrics, or demographic modeling

• Have published work on agent-based simulation, synthetic data, or LLM-based behavioral modeling

• Have worked in a high-velocity research environment where shipping matters as much as rigor

This role is based in New York City. Aaru is an in-person company, working 5 days a week in office. Candidates are expected to be located within the New York City metropolitan area or open to relocation.