Software Engineer - Voice AI

Role Summary:

We are looking for a Software Development Engineer (SDE) - Voice AI to build and scale ClickPost's centralized Voice AI platform.

ClickPost currently handles around 1 million outbound invoice calls per day and is expanding Voice AI across multiple use cases, including inbound conversations and additional communication channels. The centralized platform will power these use cases through a common infrastructure, allowing individual product teams to configure their prompts, workflows, and business logic without building the underlying Voice AI stack themselves.

You will work on the core platform responsible for Voice AI orchestration, quality, analytics, testing, iteration, scalability, and multi-channel support across Telephony, Web, and WhatsApp.

What You Will Do:

• Build and scale the centralized Voice AI platform used by multiple ClickPost products and use cases.
• Design and develop backend services for real-time voice conversations at scale.
• Build Voice AI orchestration layers integrating LLMs, Speech-to-Text (STT), Text-to-Speech (TTS), and telephony systems.
• Work extensively with Voice AI frameworks and toolkits such as Pipecat.
• Build reusable infrastructure that enables product teams to configure prompts, workflows, tools, and other Voice AI parameters.
• Develop systems for conversation quality monitoring, analytics, testing, evaluation, and continuous improvement.
• Enable Voice AI experiences across multiple channels including Telephony, Web, and WhatsApp.
• Design systems for reliable deployment, monitoring, debugging, and scaling of Voice AI applications.
• Optimize latency, reliability, cost, and conversation quality across the Voice AI stack.
• Work closely with Product and Engineering teams to understand use cases and build platform capabilities that can support them at scale.

What You Will Need:

• Strong hands-on experience in backend development and building production-grade backend systems.
• Strong practical experience with Voice AI frameworks/toolkits, particularly Pipecat or similar frameworks.
• Hands-on experience building Voice AI orchestration systems integrating LLMs, STT, and TTS.
• Experience developing real-time conversational AI or voice-based applications.
• Experience deploying and operating Voice AI applications in production environments.
• Good understanding of APIs, microservices, event-driven systems, databases, and distributed systems.
• Strong understanding of real-time communication, latency, concurrency, and reliability considerations in voice applications.
• Strong debugging and problem-solving skills with an ability to take ownership of systems end-to-end.