Principal Research Engineer

About Sondera

AI agents act on what people write, not on everything they mean. Each step can be allowed while the sequence does harm. Sondera's policy engine decides each action from everything the agent has done in the session, using natural-language rules we turn into formal policy. The same action, in the same state, under the same policy, gets the same decision, whichever vendor built the agent. The open problem underneath is semantic integrity: every action carries out what an authorized person meant. We've published our work on it at an ICML workshop and presented it at Black Hat Arsenal, BSides and [un]prompted. Our open-source hooks and policy engine already govern coding agents, and enterprise customers run our platform. Our team has built products at Cylance, Databricks, HiddenLayer, NetRise and Obsidian Security, and we're backed by Decibel, Runtime Ventures and Aviso Ventures.

About the role

You find out whether Sondera's policies hold, and make them hold better. Security engineers write rules in plain language, and we turn them into formal policy that decides what AI agents may do. You decide how we measure that policy: you run the simulations that attack and repair it, and you own the checks every policy change passes before it binds. With our Head of Research, you choose which results are ready for customers, and you ship one into the product each quarter. You'll turn our AI security research into enforceable, systems-level controls.

Principal is a senior individual-contributor role; you lead through design and review.

In your first year you will

• Define how we measure policy performance, and run simulations that attack our policies and show how to repair them.
• Build the checks a policy change passes before it binds, from replaying recorded agent activity to solver-backed analysis.
• Ship a research result into the product every quarter, with a metric and a way to roll it back.
• Measure how faithfully plain-language rules become formal policy, and improve it release over release.
• Publish or present what you learn at an ML, security or formal-methods venue.

You may be a good fit if you

• Have applied formal methods or adversarial evaluation to a real system: SMT solvers, symbolic execution, model checking, or attack and simulation harnesses.
• Write production code in whatever systems language you know best, and have shipped research code others relied on.
• Design evaluations that show when a result is wrong, not only when it's right.
• Have a public record of research: papers, talks, CVEs or open-source work.
• Use coding agents daily, and review what they write as closely as a colleague's work.

Prior security experience is useful but not required. Caring whether a control actually holds matters more.

Strong candidates may also have

• Production Rust experience.
• Red-teaming of AI agents or LLM systems, including attacks that adapt to the defense.
• Work on authorization or policy languages, such as Cedar, Rego or Datalog.
• Research on translating natural language into formal specifications.
• Program-analysis or verification tools that other engineers use.

Our stack

Rust for the services that render verdicts, Python for AI and research, and TypeScript for the web applications. Policy compiles to a formal policy language. The platform runs in Google Cloud and in customers' own infrastructure.

How we work

The people who write our papers ship the product, so what breaks in production sets our next question. We study four open problems: turning written rules into policy, enforcing that policy at runtime, making agent behavior inspectable, and overseeing fleets of agents without a person reviewing every action. We build Sondera with coding agents it governs, and a person who owns the code approves every change they make to production. Whoever builds something runs it. We work remotely and in writing, and we flag decisions we can't undo before we make them.

Logistics

• Location: Remote, United States. We meet in person three times a year.
• Compensation: Base salary of $220,000–$260,000 USD, plus equity.
• Benefits: Medical, dental and vision coverage for you and your dependents; a 401(k) plan; unlimited paid time off, and we expect you to take about a week each quarter, plus paid holidays.
• Visa sponsorship: We sponsor visas, including transfers, though not for every role or candidate.
• Interview process: screen → work-sample interview and review → research discussion → career deep dive (a structured walk through your past roles) → references. We aim to make a decision within two weeks of your screen.
• Using AI in your application and interviews: Use AI to prepare, and to polish an application you wrote yourself. In the work sample you'll build without AI, then extend your work with a coding agent, so we see both how you design on your own and how you check an agent's output. The other interviews are without AI.

We encourage you to apply even if you don't meet every qualification.