About Niural

At Niural, we're not just building products; we're redefining how companies operate in a new era of the internet driven by AI. We're creating truly global solutions that empower businesses to thrive in the digital economy. If you're eager to join a relentlessly ambitious team, develop tools that will influence the flow of billions of dollars, and share in the asymmetric financial rewards of building foundational internet infrastructure, then come help us shape the future of finance.

We are a global Payroll, Employer of Record (EOR), Agent of Record (AOR), and Contractor Management platform.

The Role

Every company we serve has to stay compliant across HR, payroll, and payments. Today most of that work is manual, sitting in the heads of experienced people and in spreadsheets. We are building Clara, our compliance agent, to do it continuously instead, starting with the United States. You are the engineer who will build her.

The hard part is not the pipeline. It is working out what compliance actually requires before you can automate it: which obligations apply, what data each check needs, where the exceptions are, and which rule wins when two of them disagree. Nobody hands you that spec. You research it from primary sources, take the open questions to our legal team, and then build it.

You do not need a legal or compliance background. You do need to be someone who can teach themselves an unfamiliar and unforgiving domain from primary sources. If you come from law, legaltech, or regtech, that is a real head start.

One thing to be clear about: in compliance, a confidently wrong answer is worse than no answer. Everything you build here has to know what it doesn't know.

What You Will Own

Research US compliance across HR, payroll, and payments

• Work out which compliance layers apply to our industry, to our platform, and to the employers and contractors on it.

• Figure out the data points each check runs on. A wage check needs salary and work location, because minimum wage varies by jurisdiction. Every layer has its own set, and some of it we do not collect yet.

• Find the exceptions and the conflicts, and settle with legal which obligation wins when two of them disagree, so the system reaches one defensible conclusion instead of surfacing a contradiction.

• Work from statutes and official guidance rather than second-hand summaries, cite your sources, and keep it current as the law changes.

Build the systems that run the checks

• Build the AI workflows that apply those rules to real platform and document data, and surface issues with a reason and a source attached.

• Build for accuracy and for abstaining when the inputs are thin, not just for coverage.

• Own model governance: prompt and model versioning, eval suites, and decision logging, so any AI-assisted compliance output can be reproduced and defended to an auditor or regulator.

Build the tools and run them in production

• Internal applications that let legal, compliance, and operations do this work directly, without an engineer in the loop.

• Integrations with our payroll engine, HR systems, and databases so nobody moves data by hand.

• Deploy, monitor, iterate, document. You own reliability, access control, and data handling for what you build.

• Use Claude Code and similar tools daily to ship at a pace that would normally need a much larger team.

Who You Will Work With

You will work continuously with Niural's legal team and our AI Product Manager. You surface the layers, data points, exceptions, and conflicts from your research; legal validates the interpretation and rules on what wins; the Product Manager sets sequencing against what the business needs next.

You are not expected to be the final authority on the law. You are expected to do the work that lets legal decide quickly, then build what comes out of it.

What We Are Looking For

Engineering

• 2+ years of software engineering experience, strong in Python and/or TypeScript.

• Hands-on experience building and deploying real applications (FastAPI, Node, React/Next.js, or equivalent).