Lead AI Engineer – Voice & LLM Systems

About the role

Venture AI is building conversational AI products for US and Gulf clients. We are looking for an AI Engineering Lead to own the technical direction of our real‑time voice stack, LLM orchestration, telephony integrations and analytics.

Key responsibilities

• Design and own the architecture of the real‑time voice AI stack (LiveKit, SIP, STT/TTS pipelines) with latency, quality and cost optimisation.
• Integrate and evaluate STT/TTS providers (Deepgram, AssemblyAI, Whisper, ElevenLabs, etc.) for multilingual support.
• Build and tune LLM‑driven dialogue systems, including prompt design, tool calling, guardrails and human hand‑off.
• Architect inbound/outbound telephony flows with SIP trunks and CPaaS providers (Twilio, Telnyx), handling routing, transfers and event webhooks.
• Develop the analytics layer: transcription post‑processing, summarisation, intent extraction, sentiment, compliance scoring and outcome tracking.
• Lead and mentor a team of AI, backend and frontend engineers, manage sprints, review code and run client demos.
• Deploy and operate services on AWS with CI/CD, security, audit logging and data‑privacy controls.

Required profile

• 6+ years of professional software engineering experience, including 2+ years leading a team.
• Hands‑on production experience with voice AI (real‑time STT, LLM, TTS) and LiveKit or comparable RTC stacks.
• Practical telephony knowledge (SIP, PSTN, Twilio/Telnyx integration).
• Strong LLM application skills (prompt engineering, function calling, evaluation).
• Experience building RAG systems and agentic workflows with LangGraph, LangChain or similar.

Required skills

• Python (FastAPI, async, WebSockets, Pydantic)
• AWS (Docker, CI/CD, GitHub Actions)
• PostgreSQL and data pipelines
• LiveKit or WebRTC‑based real‑time communication
• Telephony integration (SIP, Twilio, Telnyx)
• LLM frameworks (LangGraph, LangChain, pgvector)
• STT/TTS services (Deepgram, AssemblyAI, Whisper, ElevenLabs)

What we offer

• Lead the technical direction of a production voice AI product used on real customer calls.
• Work with the full modern voice and LLM stack from real‑time audio to analytics.
• Direct interaction with US and Gulf clients on mission‑critical systems.
• Real ownership of architecture, team and delivery.
• Competitive compensation with performance bonus, learning allowance and medical allowance.