About the role
We are looking for experienced Senior Engineers to build and scale real-time Voice AI applications. You will work across Python-based voice agents, real-time audio streaming pipelines, backend services, cloud infrastructure, and modern web interfaces.
You will collaborate directly with US-based clients and cross-functional product teams to translate business requirements into scalable, reliable and low-latency software solutions.
This is a hands-on product engineering role focused on building and deploying production-ready Voice AI applications, not just chatbots, prototypes or ML research.
The candidate will have responsibilities across the following functions:
Voice AI and Real-Time Engineering:
- Design, develop, and deploy production-grade Voice AI agents using Python.
- Work with real-time frameworks such as LiveKit, Pipecat or equivalent.
- Build end-to-end voice pipelines integrating Speech-to-Text (STT), LLMs and Text-to-Speech (TTS).
- Develop streaming audio pipelines with a focus on low latency and reliability.
- Handle audio ingestion, routing, session management, multi-party conversations and WebRTC/telephony integrations.
- Implement voice activity detection (VAD), turn detection, interruption handling, buffering and error recovery.
- Build multilingual voice workflows and troubleshoot real-time production issues.
Backend and Full-Stack Development:
- Design and develop scalable backend services using Python.
- Build asynchronous APIs, WebSockets, webhooks and event-driven pipelines.
- Develop responsive web applications using React.js / Next.js and TypeScript / JavaScript.
- Design data models, integrate third-party services and build secure data flows.
- Own product features end-to-end, from development and integration to deployment and production support.
Cloud and Production Engineering:
- Deploy, monitor, and maintain production-grade applications.
- Troubleshoot performance, latency, scalability, and reliability issues.
- Work closely with product and engineering teams to deliver robust software solutions.
Mandatory Skills:
- Strong hands-on experience with Python backend development.
- Experience building Voice AI agents or real-time audio applications.
- Knowledge of STT, LLM and TTS integrations.
- Experience with real-time streaming, asynchronous programming and WebSockets.
- Hands-on experience with React.js / Next.js and TypeScript / JavaScript.
- Experience building and deploying production-grade applications.
- Strong understanding of APIs, backend architecture and third-party integrations.
Good to Have:
- Experience with LiveKit, Pipecat or similar real-time communication frameworks.
- Knowledge of WebRTC and telephony integrations.
- Experience with multilingual voice applications.
- Familiarity with cloud platforms such as AWS, GCP or Azure.
- Experience handling VAD, turn detection, buffering, and interruption management.
- Experience working in product-based companies or fast-paced startup environments.
Ideal Candidate:
- We are looking for engineers who combine strong backend and full-stack development skills with practical Voice AI experience.
- The ideal candidate should be comfortable owning features independently, solving real-time engineering challenges, and delivering reliable products in a client-facing environment.
- Important: Candidates with only chatbot, RAG, or ML research experience, without hands-on voice AI and real-time application development, may not be a fit.