About The Role

Build phone-native AI. You will engineer the streaming pipeline, the turn-taking and the telephony that make a voice agent feel like a conversation instead of an IVR.

What You'll Do

Build streaming speech pipelines: recognition, understanding, synthesis

Engineer for sub-second end-to-end response latency

Handle barge-in, turn-end prediction and interruption gracefully

Integrate telephony and handle real-world network conditions

Build multilingual conversation support with per-language evaluation

Wire booking and CRM actions as gated tools

What You'll Bring

2+ years backend or real-time systems engineering

Python or Node.js and comfort with streaming and websockets

Understanding of audio processing basics

LLM experience with latency as a first-class constraint

Patience for debugging problems that only appear on real calls

Nice to Have

Telephony experience: Twilio, SIP or WebRTC





Speech recognition or TTS integration experience

Multilingual or Indic language speech experience

What You'd Build

These aren't hypothetical projects, they're live products you can try before your first interview.

The StackBinary MarTech Suite, The full product line, every system we ship, most with live demos.

Why Join StackBinary™?

Adaptable working hours

Remote-friendly culture

Learning & development budget

High-ownership projects

Pragmatic engineering culture

Work with cutting-edge tech

Ready to Apply?

Join our team of builders who love shipping quality software.

We connect with shortlisted candidates through LinkedIn or our official email IDs.

Follow StackBinary on LinkedIn →

Questions about this role?

[email protected]

📌 Conversational AI Engineer (Voice) (Mumbai)
🏢 Stackbinary
📍 Mumbai