Staff AI Engineer — Voice & Agentic Systems

Voxology AI is reimagining patient engagement in healthcare through AI-driven solutions. They are seeking a Principal / Staff AI Engineer to lead the design and development of their voice and agentic AI platform, focusing on creating scalable and reliable systems for healthcare interactions.

Responsibilities:

• Define and evolve the architecture of Voxology’s voice and agentic AI platform
• Design and build production-grade AI agents that can reason, use tools, manage state, and execute complex healthcare workflows
• Develop agent orchestration systems, including tool-calling, routing, memory, context management, guardrails, retries, and human escalation
• Build real-time voice AI experiences involving speech recognition, text-to-speech, turn-taking, interruption handling, and low-latency conversation management
• Architect scalable, distributed, and multi-tenant systems capable of supporting high-volume patient interactions
• Build and ship features across the stack using Python, TypeScript, React, PostgreSQL, and cloud-native infrastructure
• Design APIs, event-driven services, data pipelines, and integrations with EMR, EHR, telephony, and third-party healthcare systems
• Establish evaluation frameworks for agent quality, task completion, hallucination risk, latency, safety, and reliability
• Improve observability across AI and voice systems through tracing, structured logging, metrics, alerting, and conversation-level analytics
• Make thoughtful build-versus-buy decisions across models, infrastructure, voice providers, and AI tooling
• Lead technical design reviews and establish engineering standards for architecture, testing, security, and operational excellence
• Mentor engineers and raise the technical bar across the organization while remaining highly involved in implementation
• Partner with product, operations, leadership, and go-to-market teams to turn customer needs into scalable product capabilities
• Participate in production ownership, incident response, and continuous improvement of platform reliability