Full Stack AI Engineer

Role overview Build complete, production-grade AI products from the user interface down to the intelligence layer beneath it. The role spans web and mobile application development with large language models embedded at the architecture level rather than added on later. It suits an engineer who is equally comfortable designing a data schema in the morning and integrating an LLM pipeline by the afternoon, working on client engagements in a sprint-based delivery model.

Responsibilities - Build full-stack web and mobile applications with AI embedded as a first-class architectural concern. - Design and implement LLM integration layers, including retrieval-augmented generation pipelines, prompt engineering systems, and context management. - Collaborate directly with product and design during the discovery phase to shape what gets built, not just how. - Own features end-to-end across frontend, backend, and AI layers within sprint-based delivery cycles. - Contribute to technical architecture decisions on new client engagements. - Participate in knowledge transfer sessions so client teams can maintain delivered work after handoff.

Requirements - Three or more years of full-stack development experience using React or Next.js on the frontend and Node.js or Python on the backend. - Hands-on experience integrating large language models into production applications, with at least one shipped product rather than demo work only. - Strong understanding of API design, database architecture, and cloud deployment. - Comfort working across the full product lifecycle, from wireframe review through production deployment. - Ability to explain technical tradeoffs clearly to non-technical clients without condescension. - Genuine, active interest in the AI space, with informed opinions about new models and techniques.

Nice to have - Vector databases and embedding pipelines. - Mobile development with React Native or Flutter. - Product studio or consultancy experience. - Fine-tuning workflows.