Join a fast‑growing AI startup that is reshaping healthcare operations with voice‑first automation. You’ll lead the creation of low‑latency audio pipelines that power conversational agents handling millions of patient interactions.
What You’ll Do
- Design and run low‑latency audio pipelines for conversational agents.
- Build backend services with Python (FastAPI) and Node.js for real‑time flows.
- Implement bi‑directional streaming via WebSockets, WebRTC or RTP.
- Integrate and fine‑tune STT/TTS engines, both cloud and self‑hosted.
- Develop telephony features: call routing, recording, DTMF, and conferencing.
What You Need
- 4+ years backend engineering, focused on real‑time systems.
- Production‑grade Python and Node.js expertise.
- Proven experience building real‑time audio or voice applications.
- Deep knowledge of STT/TTS pipelines, audio codecs, and streaming.
- Hands‑on telephony integration (SIP, PSTN) and async, event‑driven design.
Good to Have
- Experience with LLM‑powered voice assistants or conversational AI.
- Familiarity with Opus, PCM, μ‑law codecs and sampling strategies.
- Cloud (AWS/GCP) autoscaling of real‑time services.
The Opportunity
Interactly.ai already supports over 2,000 physicians, delivering 20‑30% fewer no‑shows and thousands of staff‑hours saved.