Full Stack AI Developer – Voice Agent Systems
Budget: $15 – $25 USD
Location: Remote | Type: Full-time / Contract
Role Overview
We’re seeking a Full Stack AI Developer who can architect, build, and deploy AI-powered voice agent systems that integrate large language models (LLMs), speech APIs, and backend infrastructure.
You’ll work on end-to-end development — from voice conversation logic and backend APIs to real-time integrations and system deployments.
Key Responsibilities
Develop and maintain AI Voice Agents using LLMs (OpenAI, Anthropic, etc.), speech-to-text, and text-to-speech APIs.
Architect scalable full-stack applications for AI agent management, voice routing, and analytics.
Integrate with CRMs, Twilio, Slack, and other communication APIs.
Build and optimize conversational flows for natural human-like interaction.
Design and deploy backend microservices (FastAPI / Node.js) with real-time streaming capabilities.
Manage data persistence, logs, and version control through Git and CI/CD pipelines.
Ensure system uptime, security, and maintainability in production environments.
Collaborate with product, AI, and UX teams to ship new voice capabilities quickly.
Tech Stack
Backend: Python (FastAPI / Flask) or Node.js (Express / NestJS)
Frontend: React / Next.js
Databases: PostgreSQL, MongoDB, Firebase
AI Tools: OpenAI APIs, LangChain, Whisper, ElevenLabs, Deepgram, Speechmatics, Apollo
Infrastructure: AWS / GCP, Docker, GitHub Actions, REST / GraphQL APIs
Nice to Have: RAG architecture, vector DBs (Pinecone / Weaviate), WebRTC, Realtime API experience
Who You Are
3+ years of full-stack development experience with strong backend and AI integration skills.
Proven experience working with LLMs, speech recognition, and voice synthesis systems.
Solid understanding of API design, deployment, and system scalability.
Strong communicator who thrives in fast-moving, remote startup environments.
Obsessed with delivering smooth, real-time conversational AI experiences.
Must Include with Application
Two recent examples of AI or Voice Agent projects you’ve built or contributed to.
These can be:
Live product demos or GitHub repos
Client projects or prototypes
Short Loom/YouTube walkthroughs of your code or architecture
(Applications without relevant examples will not be considered.)
What We Offer
Work directly with the founding team building production-grade AI systems.
Fast-paced, product-driven culture — your work will ship live, fast.
Competitive USD compensation + performance bonuses.
Long-term growth opportunities and technical leadership paths.
The chance to help shape the future of AI employee agents used globally.
Role Overview
We’re seeking a Full Stack AI Developer who can architect, build, and deploy AI-powered voice agent systems that integrate large language models (LLMs), speech APIs, and backend infrastructure.
You’ll work on end-to-end development — from voice conversation logic and backend APIs to real-time integrations and system deployments.
Key Responsibilities
Develop and maintain AI Voice Agents using LLMs (OpenAI, Anthropic, etc.), speech-to-text, and text-to-speech APIs.
Architect scalable full-stack applications for AI agent management, voice routing, and analytics.
Integrate with CRMs, Twilio, Slack, and other communication APIs.
Build and optimize conversational flows for natural human-like interaction.
Design and deploy backend microservices (FastAPI / Node.js) with real-time streaming capabilities.
Manage data persistence, logs, and version control through Git and CI/CD pipelines.
Ensure system uptime, security, and maintainability in production environments.
Collaborate with product, AI, and UX teams to ship new voice capabilities quickly.
Tech Stack
Backend: Python (FastAPI / Flask) or Node.js (Express / NestJS)
Frontend: React / Next.js
Databases: PostgreSQL, MongoDB, Firebase
AI Tools: OpenAI APIs, LangChain, Whisper, ElevenLabs, Deepgram, Speechmatics, Apollo
Infrastructure: AWS / GCP, Docker, GitHub Actions, REST / GraphQL APIs
Nice to Have: RAG architecture, vector DBs (Pinecone / Weaviate), WebRTC, Realtime API experience
Who You Are
3+ years of full-stack development experience with strong backend and AI integration skills.
Proven experience working with LLMs, speech recognition, and voice synthesis systems.
Solid understanding of API design, deployment, and system scalability.
Strong communicator who thrives in fast-moving, remote startup environments.
Obsessed with delivering smooth, real-time conversational AI experiences.
Must Include with Application
Two recent examples of AI or Voice Agent projects you’ve built or contributed to.
These can be:
Live product demos or GitHub repos
Client projects or prototypes
Short Loom/YouTube walkthroughs of your code or architecture
(Applications without relevant examples will not be considered.)
What We Offer
Work directly with the founding team building production-grade AI systems.
Fast-paced, product-driven culture — your work will ship live, fast.
Competitive USD compensation + performance bonuses.
Long-term growth opportunities and technical leadership paths.
The chance to help shape the future of AI employee agents used globally.