Senior AI Engineer – Agentic Voice AI

Experience-

Location-

Job Summary:

We are seeking a highly skilled AI Engineer with strong expertise in Agentic Voice AI systems to design, build, and deploy real-time conversational voice agents. The ideal candidate will have hands-on experience with Pipecat, Vapi, speech-to-text (STT), text-to-speech (TTS), LLM orchestration, and API-driven system integrations. This role requires deep technical ownership from architecture to production deployment.

Key Responsibilities:

Voice AI & Agentic Systems

·        Design and develop real-time, low-latency Agentic Voice AI systems for inbound and outbound calling use cases

·        Build conversational pipelines using Pipecat (audio streaming, orchestration, event handling)

·        Implement and manage voice agents using Vapi (call flows, tool calling, webhook handling)

·        Develop agent logic with LLMs (OpenAI / Anthropic / Azure OpenAI / Gemini)

·        Implement multi-step agent workflows (intent detection, tool execution, memory, and decision-making)

Speech & Audio

·        Integrate STT services (Deepgram, Whisper, Google Speech, Azure Speech)

·        Integrate TTS services (ElevenLabs, Azure TTS, Google TTS)

·        Optimize audio streaming, turn-taking, barge-in handling, and silence detection

Backend & API Integration

·        Build and maintain REST and WebSocket APIs for real-time communication

·        Integrate with third-party systems (CRM, ticketing systems, databases, internal tools)

·        Implement secure authentication (OAuth, API keys, JWT)

·        Handle webhook-based event systems and async workflows

Infrastructure & Deployment

·        Deploy AI services using FastAPI / Flask

·        Containerize applications using Docker

·        Work with cloud platforms (AWS / GCP / Azure)

·        Monitor performance, latency, and reliability of voice systems

·        Implement logging, tracing, and error handling for production systems

Data, Evaluation & Optimization

·        Analyze call logs and conversation transcripts to improve agent performance

·        Implement prompt optimization, agent memory, and retrieval (RAG if required)

·        Optimize cost, latency, and response quality

Required Skills & Qualifications

·        Core Technical Skills

·        Strong proficiency in Python

·        Hands-on experience with Pipecat and/or Vapi

·        Experience building Agentic AI systems (tool calling, planning, memory)

·        Experience with LLM APIs (OpenAI, Anthropic, Gemini, etc.)

·        Strong understanding of real-time systems and audio streaming

Experience in below Voice AI Stack

·        STT: Deepgram, Whisper, Google, or Azure

·        TTS: ElevenLabs, Azure TTS, Google TTS

·        Telephony & Voice APIs (Vapi, Twilio, SIP concepts preferred)

·        Backend & DevOps

·        FastAPI / Flask

·        REST APIs & WebSockets

·        Docker & basic CI/CD

·        Cloud deployment experience

Good to Have (Preferred)

·        Experience with RAG pipelines (LangChain, LlamaIndex, vector databases)

·        Knowledge of call center workflows (IVR, escalation, human handoff)

·        Experience with n8n or workflow orchestration tools

·        Understanding of latency optimization for real-time AI systems

·        Prior experience building AI calling bots or voice assistants

Soft Skills

·        Strong problem-solving and debugging skills

·        Ability to own features end-to-end

·        Clear communication with technical and non-technical stakeholders

·        Startup mindset with bias toward execution