Web Developer for AI-Powered Real-Time Conversation Assistant

About the Project
We’re building an AI-powered conversation assistant that listens to live calls or meetings and provides real-time talking points, suggestions, and prompts to help users steer conversations toward a defined goal. Think of it as a smart assistant that listens quietly in the background and feeds helpful guidance throughout the conversation.

Our goal is to offer live transcription, AI-generated suggestions, and action items, all in an intuitive, user-friendly interface.

What We’re Looking For
An experienced Web Developer / Full-Stack Developer who can take the lead in building the first version of this product. You’ll work closely with me (the founder/product owner) to design, build, and integrate the various APIs and tools required.

This is a hands-on technical role, ideal for someone who’s excited by AI/ML, real-time applications, and SaaS platforms.

Core Responsibilities
Build a web-based application that streams live calls/audio (via Twilio or WebRTC).

Integrate real-time speech-to-text APIs (Deepgram, Google Cloud, AssemblyAI).

Implement OpenAI GPT-4 (or similar) to process transcriptions and generate talking points during calls.

Develop a dashboard/UI to display live transcription, AI-generated prompts, and action items.

(Optional) Integrate Text-to-Speech (TTS) for voice-based suggestions.

Ensure low latency, high reliability, and secure handling of user data.

Build post-call summaries and transcript storage functionality.

Assist with deployment and basic backend infrastructure (AWS/GCP/VPS).

Ideal Skills & Experience
Proven experience building real-time applications (WebRTC, Twilio, Agora, etc.)

Strong backend skills (Node.js, Python, FastAPI, etc.)

Proficient in integrating APIs (Speech-to-Text, NLP/LLM APIs like OpenAI, Claude, Deepgram)

Frontend experience with React.js (or Vue.js)

Experience with authentication and user management

Familiar with webhooks and streaming audio processing

Understanding of privacy/security best practices for handling call/audio data

Bonus: Experience with LLM prompt engineering and AI tools

Tools/Technologies We Plan to Use
Frontend: React.js / Next.js

Backend: Node.js / Python (FastAPI)

Real-Time Audio Streaming: Twilio Voice, Upgrade to see actual info, or Daily.co

Speech-to-Text API: Deepgram / Google Cloud Speech-to-Text

Conversational AI: OpenAI GPT-4 (Chat Completions API) or Anthropic Claude

TTS (Optional): Google Cloud TTS / Amazon Polly

Hosting: AWS / GCP / VPS

Why Work With Us?
You’ll be helping to create something truly unique—an AI tool that assists people in real-time conversations.

Freedom to choose tools and suggest better approaches.

Flexible working hours and remote work.

Opportunity for long-term collaboration as the product scales.