Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Birdeye

Principal Voice Platform Engineer (Conversational AI)

Posted Updated

Description

Principal Voice Platform Engineer (Conversational AI) Company: Birdeye Job Location: Gurugram, Haryana, India Employment Type: Full-time Experience Required: 13+ years About Birdeye Birdeye builds AI coworkers for multi-location brands. Jay for marketing, Myna for operations, and Robin for customer experience orchestrate AI agents to win AI visibility, book appointments, and drive consistent CX at every location. They run on BirdAI, the Agent OS built on 13 years of multi-location data infrastructure and 3,000+ integrations. BirdAI consolidates every signal, reasons with industry, brand and location context, and acts autonomously or with a human in the loop. Birdeye is trusted by the world's largest multi-location brands across healthcare, dental, restaurants, financial services, auto, retail, and property management. G2 ranks Birdeye #1 in Enterprise Multi-Location Marketing Platforms and named it to the 2026 Best Agentic AI Products list. Learn more at birdeye.com. Role Overview We are looking for a Senior Real-Time Voice Engineer to design, build, and optimize high-performance voice infrastructure that powers millions of automated, interactive AI voice experiences. In this role, you will own the end-to-end media pipelinehandling everything from edge routing and WebRTC streaming to real-time audio synchronization. You will work closely with our engineering teams to ensure that real-time voice interactions across phone lines and web/mobile apps are seamless, ultra-low-latency, and highly resilient under heavy enterprise scale. What Youll Do Build Streaming Media Pipelines: Design and implement highly concurrent, real-time backend systems that ingest, buffer, and process live audio streams with sub-second latency. Optimize Interactive Voice Systems: Implement core voice-handling features, including real-time speech detection, interruption handling, and streaming audio playback systems. Manage Communications Infrastructure: Configure and scale session border controllers (SBCs), media gateways, and WebRTC media servers to route multi-channel audio traffic reliably. Integrate Applied AI Frameworks: Develop secure, performant integrations with industry-leading Speech-to-Text (STT) and Text-to-Speech (TTS) streaming APIs. Own Platform Telemetry: Establish deep observability across the voice stack to track packet health, system latency, and audio quality, ensuring a high-fidelity experience for every user. What Were Looking For WebRTC & Digital Media Streaming WebRTC Protocol Internals: Strong understanding of the WebRTC stack, including SDP negotiation, ICE, STUN/TURN, and DTLS/SRTP security. Media Server Deployments: Hands-on experience working with open-source WebRTC media servers and SFU/MCU frameworks (e.g., Janus, Mediasoup, Live Kit, or Pion). Audio Optimization: Experience tuning network congestion algorithms, managing Telephony Infrastructure & Protocolsnetwork jitter buffers, and handling packet loss concealment.SBC & Gateway Management: Practical experience deploying and managing carrier-grade SBCs (e.g., Audio Codes, Ribbon) or open-source SIP proxies (Kamailio, OpenSIPS). Telephony Protocol Mastery: Deep knowledge of SIP, RTP/RTCP, and SDP state machines, including experience writing header manipulation rules. Media Capture & Transcoding: Experience with media duplication techniques (SIPREC / media forking) and audio codec mechanics (Opus, G.711) to normalize streaming data formats. Packet-Level Troubleshooting: Fluency using packet analyzers like Wireshark to diagnose signaling drops, media stream anomalies, and network delays. Modern Software & AI Infrastructure Engineering Production Coding: Fluency in either Go (Golang) or Java for building resilient backend middleware. Streaming Media Architectures: Hands-on experience with WebSockets and WebRTC for real-time bi-directional data and audio streaming.AI & Speech Models: Experience integrating streaming API endpoints with modern STT (Speech-to-Text) frameworks and TTS (Text-to-Speech) providers like ElevenLabs. Engineering Best Practices: Strong background in writing clean code, designing clean SDK/API abstractions, and managing code via Git-driven CI/CD pipelines. .

Skills

What Principal DevOps jobs ask for — and how much of it you have →
Apply

See also

DevOps jobs by country — openings, pay and top skills →