Founding AI Fullstack Engineer

The compensation package includes stock options

You Role and Purpose

As a Founding AI Fullstack Engineer at Orbio, you will be the technical architect and backbone of our intelligent HR platform. Your primary focus will be backend development using Python/Django, designing scalable AI-native architectures to orchestrate complex, autonomous recruitment workflows. You will leverage cutting-edge AI-assisted development tools like Cursor and Claude Code to rapidly prototype and ship complete full-stack features with minimal handoffs.

This is a unique opportunity to build production-grade conversational AI systems integrating LLMs, building our agent framework, using real-time voice and telephony interfaces, and zero-touch recruitment automation.

Key Responsibilities

• Architect and develop robust Python/Django backend systems for AI-driven HR workflows, multi-agent orchestration, and real-time conversational AI.
• Design and implement agentic AI workflows involving planning, context engineering, intent detection and intelligent tool calling to automate recruitment processes end-to-end.
• Build and scale conversational AI components including agentic workflows, speech-to-text (STT), text-to-speech (TTS), telephony integrations (Twilio), and voice activity detection.
• Utilize AI-assisted coding tools (Cursor, Claude Code) to accelerate full-stack feature development from backend APIs to frontend UIs.
• Ensure high code quality, implement monitoring and alerting, and maintain production reliability while shipping rapidly.
• Collaborate directly with the founders to align technical development with product vision and business goals.

Required Qualifications & Experience

• Expert-level proficiency in Python with extensive experience in Django, Django Channels, FastAPI, ASGI, and async programming.
• Strong system design skills and ability to articulate technical trade-offs.
• Proven skills in building scalable backend systems handling 100+ concurrent AI workflows with low latency.
• Deep knowledge of LLMs including prompt engineering, chaining, caching, fine-tuning, and usage of open-source (Llama, Mistral) or closed-source models (OpenAI, Anthropic).
• Experience with retrieval-augmented generation (RAG), vector databases and semantic search implementations.
• Familiarity with AI agentic frameworks, multi-agent orchestration, planning and reasoning systems.
• Hands-on experience integrating speech-to-text, text-to-speech, telephony (Twilio, IVR) and voice activity detection into production systems.
• Proficiency with AI-assisted development tools and ability to deliver full-stack features (backend + frontend) efficiently.
• Good frontend skills with JavaScript/TypeScript and React (AI-assisted vibe coding).
• Understanding of asynchronous message queues (Celery, RabbitMQ/Redis) and data storage technologies (PostgreSQL, Redis).
• English and Spanish fluency

Desired Skills

• Experience with DevOps practices: CI/CD pipelines, containerization (Docker), cloud platforms (AWS, Azure).
• Knowledge of production monitoring, logging, alerting, and security best practices for enterprise B2B AI solutions.
• Familiarity with multi-modal conversational interfaces and fallback mechanisms for robust production deployment.
• Passion for working in fast-paced startup environments with a hands-on, ownership-driven mindset.