Description
We are looking for an experienced AI Engineer to develop a real-time conversational AI voice agent with a multi-tenant architecture for our SaaS platform. The ideal candidate should have hands-on experience building production-ready AI voice assistants capable of handling natural conversations, integrating with APIs, and supporting multiple clients from a single platform. Responsibilities Develop a real-time AI voice agent with low-latency responses. Build a scalable multi-tenant architecture. Design intelligent conversation flows and dialogue management. Integrate LLMs such as OpenAI GPT or Claude. Implement speech-to-text and text-to-speech using providers such as Deepgram, ElevenLabs, or Azure Speech. Integrate telephony platforms such as Twilio, Vapi, Retell AI, or SIP providers. Connect external APIs, CRMs, scheduling systems, and databases. Build an admin dashboard for tenant management. Optimise performance, reliability, and security. Test, debug, and deploy the solution. Required Skills Python, Node.js, or TypeScript OpenAI API, Anthropic, or Gemini Vapi AI, Retell AI, Bland AI, or Twilio WebSockets and real-time streaming FastAPI, Express.js, or NestJS PostgreSQL, MongoDB, or Supabase Docker and cloud deployment (AWS, Azure, or GCP) REST APIs and Webhooks Multi-tenant SaaS architecture Git and CI/CD Nice to Have HIPAA or GDPR compliance experience RAG (Retrieval-Augmented Generation) LangChain or LlamaIndex Kubernetes Monitoring and analytics dashboards Deliverables