Senior Software Engineer (Voice AI)

Taxo•New York, NY

2d•$180,000 - $220,000•Onsite

About The Position

Leading healthcare into the agentic era. Every day, patients call their clinic to schedule an appointment, ask a question, or request a prescription refill. Behind each conversation is a busy healthcare team coordinating people, information, and systems. Taxo builds Voice AI agents that take on this administrative work. Our agents connect with EHR and practice management systems to help teams handle patient intake, complex scheduling, and refill requests, with reliable workflows and clear handoffs to people. As our Senior Software Engineer (Voice AI), you’ll report to the CTO and own defined voice-runtime services that make a voice agent useful in a real healthcare conversation. You’ll build and operate speech, turn-taking, interruption handling, tool orchestration, observability, and production fixes for the services you own, while contributing to broader platform decisions with the CTO and engineering team. This is a hands-on role with direct influence on how the product works.

Requirements

Hands-on experience shipping and operating real-time voice AI systems in production, including turn-taking, interruption handling, latency, and recovery from failures.
Strong software engineering skills and practical experience with LLMs, agent frameworks, tool calling, and external APIs.
Practical experience balancing latency, accuracy, cost, and voice conversation quality in live systems.
The ability to debug distributed systems and take ownership of reliability, observability, and testing.
Product judgment, clear communication, and a track record of moving from an ambiguous problem to a working solution.
Careful judgment around sensitive data, access controls, and safe escalation to a human.

Nice To Haves

Experience with streaming audio, SIP/VoIP, healthcare workflows, EHR integrations, or privacy-sensitive systems.

Responsibilities

Build and improve real-time voice agents for healthcare administrative workflows, including intake, scheduling, and refill requests.
Develop the conversation pipeline across speech recognition, language models, speech generation, and telephony integrations.
Improve turn-taking, interruption handling, response latency, and recovery when a conversation or external system goes off track.
Build voice-agent orchestration and tool calls on shared backend APIs and EHR connectors, partnering with the engineers who own those services and integrations.
Own voice-component tests and production instrumentation for latency, turn-taking, and tool execution. Partner with the quality engineering team on shared evaluation tooling and cross-product regression coverage.
Own voice-service observability, on-call response, diagnosis, and fixes. Use quality findings and rollout feedback to improve live voice behavior.