Voice AI Engineer
About the role
Linear Health builds voice agents that call and answer patients for US clinics. This full-time role owns those agents end to end, from the phone line to the patient record, with at least six hours of overlap with US Central time on weekdays.
What you'll do
- Own every voice agent across every customer, from the phone line to the patient record.
- Own the phone and audio layer: speech recognition, turn-taking, interruptions, silence, and latency.
- Own the agent layer: prompts, tools, conversation state, and confirmations before anything is written to a patient record.
- Bring down cost per call minute without hurting quality.
- Test and monitor so problems show up before a clinic reports them.
Requirements
- Have built real-time voice agents that took real calls in production, not demos.
- Have worked underneath the platform: LiveKit, Pipecat, Twilio, SIP, speech recognition, or turn detection. Vapi or Retell alone is not enough.
- Strong in Python and FastAPI.
- 2+ years of full-time work owning a production system.
- Can trace a bad call from the logs and prove the cause before changing anything.
- Minimum 6 hours a day of overlap with US Central time, Monday to Friday. Individuals only, full time and exclusive.
About Linear Health
Linear Health builds AI that does clinic back-office work: referrals, prior authorizations, scheduling, patient outreach, and voice agents. Customers are community health centers and specialty practices.
AI Alerts shares third-party job opportunities for informational purposes only. We are not the employer and are not involved in the hiring process. Always verify the company and role through official channels before applying, and never pay to apply, train, onboard, process documents, or secure a job offer. Legitimate employers do not ask applicants for money. Read our Terms to learn more.