Careers
Greenfield runtime. Frontier models. No legacy stack, no committees. Ship daily to analysts running real cases. Hybrid in San Mateo.
How we build
We don't bolt AI onto a workflow tool. We build the runtime, the evals, and the surfaces analysts touch. If a tool is right for the job, we use it. If it doesn't exist yet, we ship it.
Tool interfaces, planners, memory, citations, retries. Design the surfaces investigators will trust.
Anthropic, OpenAI, open-weight, in-house. We swap models like libraries, route per task, run our own evals.
Every QA disposition becomes a labeled example. The eval harness and the model fleet are the same product.
Watch your code run on a real analyst's screen. Iterate the same week. No PMs between you and the user.
Open roles
Design the agent runtime that reads SOPs, cites evidence, and ships dispositions QA and examiners trust.
Ship investigator-grade AI agents end-to-end. Tooling, evals, and the surfaces customers and analysts use every day.
Be the technical owner from first call to production. Map customer SOPs into Roe and lead the deployment.
Spend a summer building production AI agents alongside our founding engineering team. In-office in San Mateo.
We're hiring across engineering, GTM, and operations. If you've shipped investigations or AI infrastructure in regulated environments, we'd like to hear from you.