Lead Voice AI Engineer

Simpplr; Gurugram District; On-site; INR 4,500,000 - 7,000,000; Full time

Job summary

Simpplr is seeking a Lead Voice AI Engineer to build production-grade Voice Agents for frontline industries, focusing on employee support, procurement, and logistics. You will lead architecture-to-production efforts across ASR, TTS, LLMs, and enterprise workflows, ensuring compliance and high reliability.

In this hands-on leadership role, you will mentor engineers, design real-time voice runtimes, and drive end-to-end implementations with secure, scalable audio pipelines across multilingual

Qualifications

• 7+ years of software engineering experience.
• Hands-on with production distributed or real-time systems.
• Experience with Conversational AI, Voice AI, Speech AI, or LLM-based agents.
• Strong programming in Python, Java, Go, or equivalent.
• Experience with APIs, streaming systems, asynchronous architectures, and cloud-native platforms.
• Solid understanding of system design, scalability, reliability, and observability.

Responsibilities

• Design and build real-time voice runtime for live conversations.
• Develop streaming ASR, TTS, VAD, endpointing, turn-taking, and barge-in.
• Create adaptive voice pipelines for noisy frontline environments and various audio qualities.
• Architect multi-provider speech routing with real-time language detection and fallback.
• Develop Voice Agents supporting multi-turn conversations and context switching.
• Integrate Voice Agents with workflows, APIs, CRM, ITSM, and enterprise systems.
• Implement security, identity, consent, audit, and compliance controls.
• Enable warm transfer, callback, queue routing, and human handoff with context.
• Optimize multilingual voice quality and latency across environments.
• Build evaluation frameworks for WER, latency, accuracy, and CSAT.
• Establish production observability from ASR to LLM to tools to TTS.
• Evaluate and integrate leading speech, telephony, and AI technologies.
• Define architecture and production readiness for Voice AI platform.
• Mentor engineers and lead critical design reviews.

Skills

Experience with real-time systems

Conversational AI

Voice AI

Python

Java

Go

APIs and streaming

System design and observability

Tools

Deepgram

LiveKit

ElevenLabs

OpenAI

Azure Speech

Google Speech

Job description

Who We Are

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 simpplr.com.

About the role

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.

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.

This is a hands-on technical leadership role for someone who can take Voice AI from architecture to production.

Responsibilities

• Design and build the real-time voice runtime for live conversations.
• Build and optimize streaming ASR, TTS, VAD, endpointing, turn-taking, and barge-in.
• 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.
• 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.
• Develop Voice Agents that support multi-turn, multi-intent conversations, context switching, clarification, and recovery.
• Integrate Voice Agents with workflows, APIs, CRM, ITSM, knowledge bases, and enterprise systems.
• Build secure identity verification, consent, privacy, audit, and compliance controls.
• Implement warm transfer, callback, queue routing, and seamless human handoff with full conversation context.
• Optimize multilingual voice quality across accents, noisy environments, latency, and naturalness.
• Build evaluation frameworks for WER, intent accuracy, response latency, containment, resolution, escalation, and CSAT.
• Establish production observability across the full call path: ASR to LLM to tools to TTS.
• Evaluate and integrate leading speech, telephony, and AI technologies.
• Define architecture, engineering standards, and production readiness for the Voice AI platform.
• Mentor engineers and lead critical technical design reviews.

Minimum qualifications

• 7+ years of software engineering experience.
• Strong experience building production distributed or real-time systems.
• Hands-on experience with Conversational AI, Voice AI, Speech AI, or LLM-based agents.
• Strong programming skills in Python, Java, Go, or equivalent.
• Experience with APIs, streaming systems, asynchronous architectures, and cloud-native platforms.
• Strong understanding of system design, scalability, reliability, and observability.

Preferred qualifications

• Hands-on experience with Deepgram for real-time ASR and streaming speech recognition.
• Hands-on experience with LiveKit for WebRTC, real-time audio, voice-agent runtime, and session orchestration.
• Hands-on experience with ElevenLabs for low-latency, natural TTS and conversational voice experiences.
• Experience with OpenAI, Azure Speech, Google Speech, or similar ASR/TTS technologies.
• Experience with WebRTC, SIP, RTP, WebSockets, Twilio, or contact-center platforms.
• Experience with LLM agents, tool calling, RAG, LangGraph, or similar orchestration frameworks.
• Experience integrating enterprise systems such as Salesforce, ServiceNow, Jira, Zendesk, or Workday.
• Experience with multilingual speech, accent handling, noisy environments, PII redaction, and call-recording controls.
• Experience building high-scale, multi-tenant SaaS platforms.

What success looks like

• Voice Agents feel natural and responsive in real-time conversations.
• Users can interrupt naturally and change context without breaking the conversation.
• The system works reliably across languages, accents, and noisy environments.
• Voice Agents securely execute enterprise workflows and grounded knowledge retrieval.
• Complex cases escalates to humans with full context.
• The platform meets measurable targets for latency, accuracy, reliability, containment, resolution, and customer satisfaction.

Engineering principle

Voice is not chat with audio. Voice is a real-time interaction model with different requirements for latency, interruption, identity, compliance, failure handling, and human handoff.

Your Voice, Unfiltered:

We value the real you. To ensure a fair and authentic experience for everyone, we ask that you do not use AI tools (such as real-time answer generators, transcription apps, or note-taking bots) during your interview

Our process is designed to hear your unique story, thought process, and lived experience in real-time. Use of unauthorized AI tools may result in disqualification, as we want to ensure every candidate is evaluated on their own individual merits. We’re excited to meet the person behind the resume!

If you need assistive technology or AI tools for accessibility (e.g., live captioning), please notify your recruiter in advance. We are committed to providing an inclusive interview experience.

Simpplr’s Hub-Hybrid-Remote Model:

At Simpplr we believe that when work is good, life is better and that belief guides all we do. Including how we approach our flexible work model. Simpplr operates with a Hub-Hybrid-Remote model. This model is role-based with exceptions and provides employees with the flexibility that many have told us they want.

• Hub - 100% work from Simpplr office. Role requires Simpplifier to be in the office full-time.
• Hybrid - Hybrid work from home and office. Role dictates the ability to work from home, plus benefit from in-person collaboration on a regular basis.
• Role can be done anywhere within your country of hire, as long as the requirements of the role are met.