AI Backend Engineer — Low-Latency, High-Throughput
Posted
ActAI is seeking a Backend Engineer, AI to own the inference and orchestration layer powering every AI interaction in our product. You will build and operate production systems turning model capabilities into fast, stable APIs used across mobile and desktop clients.
You will design inference pipelines, manage routing, caching, batching, and state management while optimizing latency, throughput and cost. Collaborate with ML and product teams to translate model capabilities into robust,