Senior Conversational AI / Voice Integration Engineer

Senior Conversational AI / Voice Integration Engineer

OViiE AI Inc. | Orlando, FL (Hybrid/Remote)

About OViiE AI

OViiE AI is building the world’s first language infrastructure layer for global communication. Our flagship platform, STELLA, enables real-time, voice-to-voice translation across hospitality, travel, and enterprise environments—removing language barriers at the moment they matter most.

We are not building a feature.

We are building infrastructure.

With upcoming deployments aligned to FIFA World Cup 2026 host cities, OViiE AI is scaling rapidly and seeking engineers who want to build real-world, high-impact AI systems used by millions globally.

The Role

We are looking for a Senior Conversational AI / Voice Integration Engineer to lead the development of our real-time voice orchestration layer, integrating:

* ElevenLabs conversational agents

* OViiE’s proprietary Virtual Translation Rooms (VTR)

* STELLA’s enterprise SaaS platform

This role is critical in enabling live, multilingual, voice-to-voice communication across multiple participants, systems, and environments.

You will own the end-to-end conversational pipeline—from audio input to translated output to workflow automation.

What You’ll Do

* Architect and build real-time voice pipelines for conversational AI systems

* Integrate ElevenLabs agents (WebSocket-based streaming) with STELLA and VTR

* Design and implement tool-calling / function orchestration to trigger translation and workflows

* Build APIs and services that handle:

* audio streaming

* transcript processing

* translation routing

* session state management

* Develop multi-participant conversation logic (speaker routing, language detection, turn-taking)

* Connect conversational flows to enterprise systems (PMS, CRM, service workflows)

* Optimize for low latency, high concurrency, and reliability at scale

* Collaborate closely with product, ML, and design teams to deliver seamless user experiences

What You Bring

* 5+ years in software engineering, with focus on real-time systems or conversational AI

* Strong experience with:

* WebSockets / WebRTC / streaming architectures

* Node.js or Python backend development

* REST APIs and event-driven systems

* Experience integrating or working with:

* LLMs or conversational AI frameworks

* speech systems (ASR/TTS)

* voice APIs (e.g., ElevenLabs, Twilio, etc.)

* Understanding of:

* multi-turn dialogue systems

* tool/function calling in LLM environments

* latency optimization in real-time applications

Bonus Points

* Experience with multilingual systems or translation pipelines

* Familiarity with NVIDIA Riva / NeMo / speech AI frameworks

* Experience building multi-user or session-based platforms

* Background in hospitality, travel tech, or real-time communication platforms