Founding Software Engineer
Core
Building an AI-native, real-time medical interpretation platform enabling voice-to-voice communication between clinicians and patients across languages.
Role type
Founding full-stack engineer (agentic AI & real-time streaming)
Builds
Real-time audio/video pipeline, voice agent connecting patients/providers/AI, clinician-friendly web client
Domain
Healthcare / AI / Real-time communication
Deliverable
production ML models | product features | infrastructure
Required skills
Full-stack engineering, Next.js/React, WebRTC/MediaStream APIs, backend development (Go/TypeScript/Python), SQL, cloud infrastructure, CI/CD
Preferred skills
Agentic AI, voice agents, NLP, speech recognition/synthesis, audio signal processing, LiveKit, Twilio, SIP, VoIP, regulated domain experience
Technologies
Next.js, React, WebRTC, MediaStream APIs, Go, TypeScript, Python, SQL, LiveKit, Twilio, SIP
Responsibilities
Architect provider/patient-facing web app and own WebRTC layer (media negotiation, audio routing, reconnection, observability); Design agentic behavior of AI interpreter and multilingual agent; Drive product strategy via customer calls and clinic visits; Build engineering team and set technical direction
Seniority
Founding, high autonomy IC