Job Role: AI Voice Platform Developer Intern
Location: Remote (India)
Type: Full-time Internship (6 months, convertible to full-time)
Stipend: ₹10,000/month
Start Date: Immediate
About the Role
We're building an AI voice agent platform that US agencies resell to their clients (dental clinics, home services, real estate).
You'll be working on the full stack — from the voice agent configuration engine to the agency dashboard to Azure cloud infrastructure. This is a ground-floor role in a product being built for the US market with real paying customers.
What You'll Do
- Build and maintain the backend API (Node.js/Express) that powers multi-tenant voice agent management
- Develop the agency-facing dashboard (React/Next.js) where agencies configure agents, view call logs, and manage their clients
- Integrate with third-party APIs: Retell AI (voice agents), Twilio (telephony/SMS), Google Calendar, Stripe (billing)
- Set up and manage Azure infrastructure: App Service, Cosmos DB, Blob Storage, Azure OpenAI
- Write webhook handlers that process real-time call events (call started, appointment booked, escalation triggered)
- Help design the database schema and multi-tenancy architecture
- Write clean, documented code with tests
- Participate in daily standups and weekly demos
What We're Looking For
Must Have
- Strong JavaScript/TypeScript skills (Node.js backend + React frontend)
- Familiarity with REST API design and integration with third-party APIs
- Basic understanding of databases (SQL or NoSQL — we use Cosmos DB)
- Hands-on experience with Whisper (OpenAI's speech-to-text model) — running it self-hosted or via API, tuning for latency/accuracy
- Hands-on experience with open-source voice/speech LMs for TTS (e.g., CSM/Sesame, StyleTTS2, or similar) — running inference, voice selection/cloning, integrating into a real-time pipeline
- Git proficiency (branching, PRs, code review)
- Can work US-overlapping hours (at least 3–4 hours overlap with US Eastern, i.e., evening IST)
- Good written English (you'll read US client requirements and write documentation)
- Self-starter who can take a spec and run with it without daily hand-holding
Nice to Have
- Experience with Azure (App Service, Functions, Cosmos DB) or any major cloud
- Experience with Twilio, telephony/VoIP concepts, or WebSocket/real-time systems
- Familiarity with AI/LLM APIs (OpenAI, Anthropic, or Azure OpenAI)
- Experience with multi-tenant SaaS architecture
- Prior work with turnkey voice AI platforms (Retell, Vapi, Deepgram)
- Experience with Stripe integration or billing systems
- GPU inference experience (CUDA, ONNX Runtime, or similar) for running self-hosted models efficiently
Personality Fit
- Curious about AI and voice technology
- Comfortable working in a fast-moving, small-team environment
- Willing to learn new tools and services quickly (you'll touch 8–10 different APIs)
- Takes ownership — "I figured it out" matters more than "nobody told me"
What You'll Learn
- How to build and ship a real SaaS product for the US market
- Multi-tenant architecture patterns used by products like GoHighLevel, Twilio, etc.
- Voice AI and telephony (a high-demand, high-paying skill set)
- Azure cloud platform (certifiable skills)
- Working with US agencies and understanding their business model
- End-to-end product development: from architecture to deployment to customer feedback
How to Apply
Send your resume and a brief note (2–3 sentences) on why this role interests you to [[email protected]]. Bonus points if you include a link to a project you've built that involves API integrations.
Subject line: "AI Voice Platform Intern — [Your Name]"
We're a small, fast-moving team building AI products for the US market from India. If you want to learn fast, ship real things, and work on technology that's genuinely cutting-edge, this is the role.
Pay: ₹10,000.00 per month
Benefits:
- Flexible schedule
- Work from home
Work Location: Remote
