AI Voice Engine Developer

Job Description

One of our clients, a fast-growing Digital Marketing startup with a global presence, is looking for an AI Voice Engine Developer to join its team in Coimbatore. The ideal candidate will play a crucial role in developing high-performing AI-powered voice applications and real-time conversational systems. This position is ideal for a self-driven and technically skilled professional passionate about AI voice solutions and end-to-end development.

Job Title : AI Voice Engine Developer

Location : Coimbatore

Job Type : Full-Time (Onsite)

Key Responsibilities :

Design and implement real-time AI voice agent systems using Twilio for inbound and outbound calls.

Develop backend services using FastAPI or Express.js for voice session control, call routing, and AI response management.

Integrate Speech-to-Text (STT) and Text-to-Speech (TTS) APIs such as Whisper, Deepgram, ElevenLabs, and OpenAI TTS .

Build and optimize real-time audio streaming pipelines using WebRTC , RTP , or Twilio Media Streams .

Implement Large Language Models (LLMs) like GPT-4 / OpenAI Realtime for contextual AI-driven conversations.

Manage session memory, call context, and message states using Redis or similar technologies.

Handle call recording, transcription, and analytics pipelines .

Collaborate with AI engineers and frontend teams (React / Next.js) to ensure full system integration.

Focus on optimizing latency, reliability, and performance in low-latency environments.

Requirements :

Strong proficiency in Python (asyncio, FastAPI) or Node.js (Express.js).

Proven experience with Twilio Voice , WebRTC , or similar real-time communication frameworks.

Experience integrating speech APIs (Whisper, Deepgram, Google Speech, OpenAI TTS, etc.).

Working knowledge of LLM APIs (OpenAI GPT, Anthropic Claude, etc.).

Solid understanding of event-driven architectures (WebSocket, Pub / Sub).

Experience with PostgreSQL , SQLAlchemy / SQLModel , and Docker .

Familiarity with REST API design and backend architecture best practices.

Strong debugging, analytical, and problem-solving skills.

Ability to work independently, manage time efficiently, and meet project deadlines.

About the Client :

Our client, a digital marketing agency that helps brands get noticed. Their services include Website Development, SEO, Social Media Marketing, PPC, Email Marketing, and Content Creation . What sets apart is their commitment to continuous learning, innovation, and teamwork. Every challenge is viewed as an opportunity to grow, and collaboration lies at the heart of everything they do.

If you are passionate about building intelligent, AI-driven voice systems and want to work in a dynamic, innovation-focused environment, this is the perfect opportunity for you.

Interested candidates can drop their resume at :   jobs@prognova.co

Requirements

Python (asyncio, FastAPI), Node.js (Express.js), Twilio Voice, WebRTC, Whisper, Deepgram, Google Speech, OpenAI TTS, LLM APIs (GPT, Claude), WebSocket, Pub / Sub, PostgreSQL, SQLAlchemy, SQLModel, Docker, REST API design, Streaming audio (WebRTC, RTP), Debugging, Problem-solving, Optimization skills, Independent and time management skills.