A product-led SaaS company in Dublin is seeking an engineer experienced in building reliable, scalable LLM systems for production. You will design and deploy RAG pipelines, improve inference latency, and embed AI features in collaboration with backend and product teams. The ideal candidate has a strong understanding of backend fundamentals and real-world trade-offs in system design. This role offers a dynamic environment focused on the integration of AI technologies into core platform functionality.
#J-18808-Ljbffr