Principal Research Engineer

What you will do:

• 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.

Who you are:

• 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.

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.