What you'll do
- Design and ship agent runtimes for voice (telephony, ASR/TTS, state machines) and browser (Playwright-based, vision-assisted) channels.
- Build the escalation path: how an agent pauses, hands context to a human, and resumes.
- Instrument everything. If a specialist can't replay a session, we shipped it wrong.
- Pair weekly with retrieval ops; listen to calls; fix what you hear.
What we're looking for
- 5+ years building production systems; you've run something on-call.
- Comfortable across the stack: Python or TypeScript services, a bit of infra, enough frontend to build a debugging UI.
- Have worked with LLM or speech APIs in production and have opinions about where they fail.
- Care about health data. Bonus if you've touched HL7, FHIR or a portal in anger.
How we hire
Four steps, two weeks if you want it that fast. A 30-minute call with the hiring manager. A practical exercise related to the role (paid, if it takes more than two hours). A half-day with the team, in person or remote, including a session listening to real retrieval calls. Then references and an offer.
Benefits
- Meaningful equity at a seed-stage company
- Full health coverage for you and dependents
- Paris and Boston offices, or remote within EU / US time zones
- Six weeks' leave, plus local public holidays
- Annual learning budget, hardware of your choice, relocation support
Apply
Thanks, there.
We read every application ourselves and reply within a week, either way.
Also open in Engineering