SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Commure is building an AI Operating System for healthcare, with a platform spanning ambient AI documentation, intelligent agents for workflow automation, and autonomous revenue cycle management. The company processes $25B+ in annual claims across 500+ healthcare organizations and supports 200+ million patient interactions. Commure recently raised $70M at a $7B valuation and was named to Fortune's Future 50 list and 2026 AI Breakthrough Awards for "Overall NLP Company of the Year."
Health system call centers struggle to keep up with patient demand—85% of patients who can't reach someone never call back. Commure is building AI Voice Agents that answer every call and handle the full conversation: scheduling, rescheduling, cancellations, confirmations, FAQs, and intake. These agents integrate directly with EHR and telephony systems in real time.
You will build the backend systems powering these voice agents. This is a mid-level role on a small, fast-moving team that ships daily. Your responsibilities include:
- Build backend services in Python powering real-time voice agents: call orchestration, conversation state, tool execution, and EHR write-back.
- Contribute to low-latency pipelines connecting telephony, ASR, LLMs, and TTS into a single conversational loop.
- Integrate with healthcare systems (Epic, Cerner, athena, and others) for scheduling, eligibility, and intake.
- Collaborate with senior engineers to design APIs, data models, and event-driven workflows.
- Partner with AI, product, and operations teams to ship features that patient access teams actually use.
- Own the quality of what you ship: latency, reliability, observability, and release readiness.
The role is full-time, in-office in Mountain View, CA, 5 days per week.
**Requirements:**
- 2–4 years of backend software experience, primarily in Python.
- Experience shipping production services, APIs, and data models.
- Intuition for how people interact with automated assistants through voice and text (different interaction patterns than UI).
- Comfort with async, event-driven, or real-time systems (or enthusiasm to grow into them).
- Strong fundamentals in testing, LLM evaluation, observability, and reliability.
- Patient-centered mindset: design for the person on the other end of the line, not just metrics.
- Bias for action and ownership mindset.
