- Build human-like AI voice agents using LLMs, STT, and TTS.
- Create real-time STT → LLM → TTS pipelines.
- Design natural conversations, prompts, interruptions, and multi-turn flows.
- Optimize latency, conversation quality, and CX.
Experience Required
- 5–9+ years in Software Engineering.
- Minimum 2+ years in VoiceBots / Conversational AI.
- Hands-on experience building production-grade AI voice systems.
- Prior experience in an AI / Voice AI / Conversational AI company preferred.
Required Skills
- Strong in LLMs & prompt engineering.
- Backend: Python / Node.js.
- Familiar with speech tech like Whisper, Deepgram, Google STT, Azure Speech.
- Understanding of realtime voice streaming & telephony systems preferred.
Tech Stack :
STT: Whisper, Deepgram, Google STT, Azure Speech
TTS: ElevenLabs, Azure TTS, PlayHT, Coqui
LLMs: OpenAI, Claude, Vertex AI, Llama
Telephony: SIP, WebRTC, FreeSWITCH, Asterisk
Backend: Python / Node.js / Golang
Infra: AWS / GCP, Docker, Kubernetes
Realtime: WebSockets, streaming pipelines
Salary :
Best in class
