AI Voice Agent Engineer (Real‑time Conversational AI)

About the role

We are seeking a highly skilled AI Voice Agent Engineer to design, build, and optimize real‑time conversational AI systems. You will work on voice agents that leverage large language models (LLMs) and advanced streaming technologies to deliver seamless, low‑latency interactions.

Key responsibilities

• Build and optimize real‑time AI voice agents.
• Develop scalable backend APIs and streaming systems using FastAPI and related technologies.
• Integrate LLMs, function calling, and tool‑calling workflows.
• Implement conversational memory, retrieval‑augmented generation (RAG) pipelines, and context management.
• Improve latency, interruption handling (barge‑in), and overall voice interaction quality.
• Deploy, monitor, and maintain production‑grade AI services in containerised environments.

Required profile

• Strong problem‑solving abilities.
• Hands‑on experience with production AI systems.
• Familiarity with scalable backend architecture and microservices.
• Passion for conversational AI and voice technologies.

Required skills

• Python (mandatory)
• FastAPI (mandatory)
• Node.js (preferred)
• LiveKit
• Google Gemini API
• OpenAI API
• Streaming audio processing
• Voice Activity Detection (VAD)
• Turn detection / barge‑in handling
• Function calling / tool calling
• Low‑latency conversational AI systems
• LLM & Agent frameworks (LangChain, Prompt Engineering, Agent orchestration)
• Context management, conversation memory, structured outputs
• RAG (Retrieval‑Augmented Generation)
• Vector databases (Qdrant, Pinecone)
• REST APIs, WebSockets, async programming, streaming APIs
• Microservices architecture
• Docker
• CI/CD pipelines