Software Engineer, Applied AI

Aaru builds simulations of human behavior. Each simulation contains a population of AI agents, each representing a person who could plausibly exist in the real world and capable of making decisions within a modeled environment. Companies and institutions use these simulations to test consequential choices before committing—from product launches and pricing decisions to strategic communications and policy changes.

Building a useful simulation requires more than generating plausible text. Populations must represent real people and groups; predictions must be calibrated; simulations must remain coherent as conditions change; and the product must make the resulting evidence legible enough to support real decisions.

We are a small, in-person team in New York. We work with urgency, high ownership, and intellectual honesty. We expect people to surface inconvenient evidence, change their minds quickly, and carry important work all the way to a result.

The Applied AI team works across the stack to improve Aaru's simulation pipelines and explore new product areas where simulations can be useful. The work can range from infrastructure and platform systems to frontend experiences and APIs. It is organized around the highest-leverage initiatives the company is pursuing, rather than a fixed technical domain. Applied AI Engineers own outcomes across the stack and work cross-functionally with other engineering teams and GTM teams such as Deployment to ensure that what we build becomes a strong product and developer experience.

As an Applied AI Engineer, you will work on high-leverage initiatives at the intersection of AI systems, simulation infrastructure, and product development. You will improve existing capabilities, help prototype and evaluate promising company bets, and turn experimental ideas into reliable systems. The work is initiative-driven rather than defined by a fixed product roadmap or a single layer of the stack.

You will work primarily in Python and TypeScript, but you will use whatever technologies are necessary to finish the job. You will move from an ambiguous problem to a working system: understand the problem, find the smallest useful experiment, improve the architecture, evaluate the result, deploy it, and continue iterating based on evidence.

This is a role for a strong general software engineer who wants to work in an AI-native environment. Prior experience with AI or agent systems is helpful, but the more important qualities are sound engineering judgment, curiosity, and the ability to learn quickly across unfamiliar parts of a system.

• Improve agent functionality within Aaru's product, including interaction design, tool use, context handling, orchestration, reliability, and model behavior.

• Optimize simulation pipelines to increase throughput, remove bottlenecks, and make large or repeated runs more efficient.

• Build evaluation harnesses and supporting architecture that make agent and simulation capabilities testable, reproducible, and easier to improve.

• Help prototype and evaluate promising company bets through focused experiments and technical investigations, then help build out the ideas that merit further investment.

• Work cross-functionally with other engineering teams and GTM teams such as Deployment to make new capabilities usable, supportable, and dependable in real workflows.

• Write clear technical designs and documentation. Make assumptions, dependencies, tradeoffs, and unresolved risks legible to the rest of the organization.

Applied AI work is open-ended. We get close to the problem, reduce it to the smallest useful experiment, and use evidence to decide what to do next. We move quickly, but we do not confuse a compelling prototype with a finished system or hide uncertainty behind polished demos.

AI-native engineering requires looking across software, models, data, evaluation, and operational behavior. We expect engineers to learn unfamiliar parts of the stack, question assumptions, and improve the architecture when the first approach does not hold up.

We prefer small teams and clear ownership. The person closest to a problem should have the context and authority to make decisions, while documenting enough that the rest of the organization can understand and challenge them. Cross-functional work should make dependencies, tradeoffs, and risks visible.

• You are comfortable with loosely specified problems and can turn ambiguity into a useful next step.

• You have strong general software engineering fundamentals and can work across layers when the problem requires it.

• You enjoy fast iteration and are willing to change direction when evidence points somewhere else.

• You care about testability, evaluation, performance, maintainability, and the difference between a demo and a dependable system.

• You take responsibility for outcomes through implementation, deployment, measurement, and iteration.

• You communicate directly, work well across functions, and make technical tradeoffs clear to people with different backgrounds.

• You want to build AI-native systems whose impact is not bounded by a single technical domain.

• Experience building AI-native products, agents, LLM applications, or other systems in which model behavior materially shaped the user experience.

• Experience building evaluation tools, test harnesses, reproducible fixtures, or systems for detecting regressions in complex behavior.

• Experience improving throughput, performance, or reliability in data, compute, or workflow pipelines.

• Experience working at an early-stage company or on projects where you owned a broad problem from initial idea through production.

• Fluency with technologies such as Python, TypeScript, React, APIs, workflow systems, relational data models, and cloud infrastructure—or equivalent depth in a comparable stack.

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

Aaru offers a competitive base salary, equity participation, comprehensive medical, vision, and dental coverage, visa sponsorship and relocation support, and other benefits and perks. Final compensation depends on level and experience and is set within Aaru's internal bands.