Plivo

About the Role

We’re seeking Senior Software Development Engineers with deep expertise in Voice Communication Systems, Real-Time Audio Processing, and Conversational AI integration. You will play a critical role in building the core systems that power our AI Voice Agent Platform enabling seamless, scalable, and intelligent voice interactions for a variety of customer engagement use cases.

Responsibilities

• Design and develop scalable, reliable, low-latency systems for handling real-time voice calls and audio streams powering AI agents.
• Improve the core voice platform to enable Voice AI Agents by adding AI based noise cancellation, interruption detection, turn detection etc.
• Integrate speech technologies (ASR, LLMs, TTS) and orchestrate them with voice infrastructure for intelligent conversations.
• Work closely with product managers, designers, and AI/ML engineers to translate customer needs into technical features.
• Lead architecture reviews and make technology decisions for high availability, fault tolerance, and voice quality optimization.
• Champion software engineering best practices.
• Ensure platform observability through monitoring, logging, and tracing tools.

Qualifications

• 3+ years of experience in backend development, with experience in real-time voice/audio systems.
• Deep knowledge of SIP, WebRTC, RTP, VoIP protocols, and media servers (e.g. , FreeSWITCH, Livekit or custom WebRTC servers).
• Proficiency in building scalable microservices using languages like C,Go or Python.
• Strong understanding of networking, distributed systems, and cloud-native architecture (Kubernetes, Docker, etc.)
• Experience working with cloud providers (AWS, GCP, or Azure), especially in deploying and scaling real-time applications.
• Prior experience building platforms for AI agents, bots, or CPaaS.
• Contributions to open-source voice or AI tools.
• Experience integrating conversational AI components.