AI Full Stack Engineer

Description Jeen.AI is an enterprise AI platform that enables organizations to build, deploy, and scale advanced AI agents, automations, and knowledge-driven systems across cloud and on-prem environments. We provide a secure and flexible foundation for companies to integrate AI deeply into their operations. Under Jeen, Jeen Talk is a dedicated product line focused on building a B2C AI platform for enterprises - enabling businesses to create and deploy real-time voice and chat agents that interact directly with customers at scale. We are looking for a highly motivated AI Full Stack Engineer to join the Jeen Talk team and help build the next generation of real-time AI voice systems. Why Join us? Build a real production-grade voice AI platform Work on real-time systems at scale Be part of a fast-growing AI company with real enterprise traction Own features end-to-end - from idea to production Work with cutting-edge AI + voice technologies Responsibilities At Jeen Talk, you’ll work across the full stack - from real-time audio pipelines to scalable backend systems and modern frontend interfaces. Develop AI-powered voice agents using modern voice frameworks Build and maintain FastAPI-based REST APIs with complex session and webhook logic Develop React + TypeScript frontend with real-time audio and data visualization Build Python microservices for Transcription, Call analysis, Alert scheduling (Celery) Integrate leading AI providers LLMs (OpenAI, Azure, Google), TTS / STT engines Design and improve real-time voice infrastructure and telephony (SIP/VoIP) systems Take part in architectural decisions across the platform Ensure high code quality with testing and best practices Requirements 4+ years of full-stack development experience with React + TypeScript, Python (FastAPI or similar async frameworks) Experience with: SQLAlchemy, Alembic, Pydantic v2, PostgreSQL, Redis Solid understanding of REST API design (auth, webhooks, multi-tenant systems), Async systems and task queues (Celery) Experience integrating LLM APIs (OpenAI, Azure, Gemini) Familiarity with STT/TTS providers Strong understanding of real-time systems and latency tradeoffs Strong communication skills (English & Hebrew) Ability to think critically about Model limitations, Hallucinations and Performance vs cost tradeoffs. Deep understanding of software engineering methodologies, including design patterns and scalable system design. Preferred Qualifications Experience building real-time voice AI systems SIP / VoIP / telephony integration experience Experience with RAG pipelines, Vector databases / embeddings Familiarity with MCP (Model Context Protocol) Experience with on-prem / self-hosted AI deployments Experience with search systems (MeiliSearch / OpenSearch / similar) Strong product thinking - ability to surface risks before they become production issues