Location: Hybrid, New Delhi
Type: Full-Time
Experience: 13 Years
About Us
Eazybe is an AI tool that connects your WhatsApp to your CRM, like HubSpot or Zoho. It lets you manage leads and update deals directly from your chat window so you never have to switch between tabs.
Our smart AI Agents work 24/7 to handle the repetitive parts of your job, like answering basic questions and syncing data. This keeps your records organized and lets your team focus on talking to customers and growing the business.
Role Overview
We are seeking a Voice AI Developer to join our engineering team as we scale our conversational AI capabilities. In this role, you will be responsible for designing, developing, and optimizing the voice-first experiences within our SaaS platform. You will work at the intersection of Speech-to-Text (STT), Natural Language Processing (NLP), and Text-to-Speech (TTS) to build low-latency, human-like conversational agents that integrate directly with our core product ecosystem.
The ideal candidate has a foundational understanding of Large Language Models (LLMs) and a passion for solving the unique challenges of real-time audio processing in a cloud-based environment.
Key Responsibilities
- Pipeline Development: Build and maintain production-grade voice pipelines using state-of-the-art models (e.g., Whisper, Deepgram, ElevenLabs).
- Latency Optimization: Engineer solutions to minimize turn-taking delay, ensuring real-time responsiveness for end-users.
- SaaS Integration: Develop and document robust APIs and webhooks to connect voice interactions with our backend services and third-party CRMs.
- LLM Implementation: Utilize frameworks like LangChain or LangGraph to manage conversational state, tool-calling, and RAG (Retrieval-Augmented Generation).
- Testing & Quality: Monitor and improve system performance using metrics like Word Error Rate (WER) and sentiment accuracy.
- Collaboration: Work closely with Product and UI/UX teams to refine the Voice User Interface (VUI) and ensure a seamless customer journey.
Required Qualifications
- Experience: 13 years of professional software development experience, with at least 1 year focused on AI, NLP, or Voice technologies.
- Programming: High proficiency in Python (FastAPI, Flask, or Asyncio).
- AI Knowledge: Hands-on experience with LLM orchestration and prompt engineering.
- Web Protocols: Solid understanding of WebSockets, WebRTC, or gRPC for streaming audio data.
- Cloud Infrastructure: Experience deploying and scaling applications on AWS, GCP, or Azure using Docker.
- Problem Solving: A proven ability to troubleshoot complex, non-deterministic AI behaviors.
Preferred Qualifications (Nice-to-Haves)
- Experience with specialized voice platforms like Vapi, Retell AI, or LiveKit.
- Familiarity with Vector Databases (e.g., Pinecone, Weaviate, or Milvus).
- Background in audio signal processing (noise reduction, echo cancellation, or VAD).
- Previous experience in a high-growth B2B or B2C SaaS environment.
