Lead Voice AI Engineer

<div class="content-intro"><h3><strong>Who We Are</strong></h3> <p>Simpplr is the AI-powered intranet for unifying the digital workplace. It brings people, trusted knowledge, apps, and agents into a coherent digital experience. Powered by a proprietary EX Knowledge Graph, Simpplr synthesizes signals and context across connected systems to deliver personalized information and actions. The platform serves as a digital hub supporting communications, engagement, employee services, and work. With low-code extensibility and enterprise-grade security and governance, Simpplr enables confident operation at scale. More than 1,000 organizations — including AAA, the NHS, Penske, and Moderna — trust Simpplr to keep their workforce informed, aligned, and productive. Learn more at <a href="http://simpplr.com">simpplr.com</a>.</p></div><h1>About the role</h1> <p>We are looking for a Lead Voice AI Engineer to build production-grade Voice Agents for frontline heavy verticals like healthcare, manufacturing, warehousing, retail, hospitality focusing on employee support, procurement, collections, logistics, ordering etc.</p> <p>You will lead the design of low-latency, real-time voice systems combining ASR, TTS, LLMs, conversational AI, enterprise workflows, knowledge retrieval, compliance, and human handoff.</p> <p>This is a hands-on technical leadership role for someone who can take Voice AI from architecture to production.</p> <h1>Responsibilities</h1> <ul> <li>Design and build the real-time voice runtime for live conversations.</li> <li>Build and optimize streaming ASR, TTS, VAD, endpointing, turn-taking, and barge-in.</li> <li>Build adaptive voice pipelines for high-noise frontline environments (60-112 dB), hospitals, factory floors, warehouses, including server-side noise cancellation, echo suppression, and dynamic ASR/TTS optimization for PSTN and mobile phone audio quality.</li> <li>Architect multi-provider speech routing across a broad multilingual matrix, including code-switching (e.g., Spanglish, Hinglish), where no single ASR or TTS provider covers all languages, and language detection, provider selection, and fallback chains must operate in real time mid-call.</li> <li>Develop Voice Agents that support multi-turn, multi-intent conversations, context switching, clarification, and recovery.</li> <li>Integrate Voice Agents with workflows, APIs, CRM, ITSM, knowledge bases, and enterprise systems.</li> <li>Build secure identity verification, consent, privacy, audit, and compliance controls.</li> <li>Implement warm transfer, callback, queue routing, and seamless human handoff with full conversation context.</li> <li>Optimize multilingual voice quality across accents, noisy environments, latency, and naturalness.</li> <li>Build evaluation frameworks for WER, intent accuracy, response latency, containment, resolution, escalation, and CSAT.</li> <li>Establish production observability across the full call path: ASR → LLM → tools → TTS.</li> <li>Evaluate and integrate leading speech, telephony, and AI technologies.</li> <li>Define architecture, engineering standards, and production readiness for the Voice AI platform.</li> <li>Mentor engineers and lead critical technical design reviews.</li> </ul> <p> </p> <h1>M∂inimum qualifications</h1> <ul> <li>7+ years of software engineering experience.</li> <li>Strong experience building production distributed or real-time systems.</li> <li>Hands-on experience with Conversational AI, Voice AI, Speech AI, or LLM-based agents.</li> <li>Strong programming skills in Python, Java, Go, or equivalent.</li> <li>Experience with APIs, streaming systems, asynchronous architectures, and cloud-native platforms.</li> <li>Strong understanding of system design, scalability, reliability, and observability.</li> </ul> <p> </p> <h1>Preferred qualifications</h1> <ul> <li>Hands-on experience with Deepgram for real-time ASR and streaming speech recognition.</li> <li>Hands-on experience with LiveKit for WebRTC, real-time audio, voice-agent runtime, and session orchestration.</li> <li>Hands-on experience with ElevenLabs for low-latency, natural TTS and conversational voice experiences.</li> <li>Experience with OpenAI, Azure Speech, Google Speech, or similar ASR/TTS technologies.</li> <li>Experience with WebRTC, SIP, RTP, WebSockets, Twilio, or contact-center platforms.</li> <li>Experience with LLM agents, tool calling, RAG, LangGraph, or similar orchestration frameworks.</li> <li>Experience integrating enterprise systems such as Salesforce, ServiceNow, Jira, Zendesk, or Workday.</li> <li>Experience with multilingual speech, accent handling, noisy environments, PII redaction, and call-recording controls.</li> <li>Experience building high-scale, multi-tenant SaaS platforms.</li> </ul> <p> </p> <h1>What success looks like</h1> <ul> <li>Voice Agents feel natural and responsive in real-time conversations.</li> <li>Users can interrupt naturally and change context without breaking the conversation.</li> <li>The system works reliably across languages, accents, and noisy environments.</li> <li>Voice Agents securely execute enterprise workflows and grounded knowledge retrieval.</li> <li>Complex cases escalate to humans with full context.</li> <li>The platform meets measurable targets for latency, accuracy, reliability, containment, resolution, an