Role: Own conversational prompt design for client voice AI agents and tune the pipeline (ASR/LLM/TTS config) for latency and naturalness. This is applied engineering, not infra ownership.

Responsibilities

- Design/iterate prompts per client use case (flows, tone, escalation, RAG)
- Tune ASR/TTS parameters and LLM configs for latency, interruption handling, natural turn-taking
- Integrate Mem0 for session memory
- Evaluate and select LLM/S2S models (GPT, Claude, Gemini) per client need
- Build lightweight eval sets to test changes pre-deployment

Requirements

- 4–7 yrs conversational/voice AI, hybrid prompt + applied ML background
- Hands-on with ASR/STT (Whisper, Deepgram, Azure/Google STT), LLM APIs, RAG
- Python; comfortable reading/modifying pipeline code, not just prompting

Clarion.ai specializes in delivering enterprise-grade AI solutions focused on operational excellence and real-world impact. We bridge the gap between AI potential and production-ready implementation.

- Corporate Site: https://clarion.ai/
- LinkedIn: https://www.linkedin.com/company/clarion-analytics-singapore/
- https://voicevertex.ai/

Pay: ₹250.00 - ₹1,000.00 per hour

Work Location: Remote

📌 Voice AI Conversation Engineer (India)
🏢 Clarion Analytics
📍 India