Full-Stack AI Engineer for Voice Agent

Job Opportunity: Full-Stack AI Engineer for Voice Agent Development

We’re looking for an experienced AI & Full-Stack Engineer to help us build a production-ready Voice Agent. The goal is to integrate real-time telephony with conversational AI, delivering seamless natural voice interactions.

Required Skills

Twilio – Call handling, SIP/WebRTC integration, real-time media streams.

Rasa – Conversational AI (NLU, dialogue management, intent/entity handling).

Google Cloud Speech-to-Text & Whisper – Speech recognition pipelines with fallback/latency optimization.

React – Frontend dashboard/agent console with real-time updates.

Express/FastAPI – Backend API for orchestration, authentication, and middleware.

What You’ll Build

A Voice AI Agent that receives calls via Twilio, transcribes audio in real-time (Google STT + Whisper), and routes text to Rasa for intelligent responses.

A backend service (Express or FastAPI) to manage conversation orchestration, retries, and logging.

A React frontend to visualize conversations, logs, and usage metrics.

Nice to Have

Experience with Docker/Kubernetes for deployment.

Knowledge of vector DBs (Pinecone, Weaviate) for RAG-style context injection.

Familiarity with OpenAI/Anthropic APIs for fallback LLM responses.

NOTE: if you don’t have past working links, you will be ignored. Please share your portfolio/examples (applications without relevant examples will not be considered).