Backend Engineer - AI Systems & Inference Pipelines
Summary
Builds and optimizes AI inference pipelines and orchestration layers for a smart assistant, ensuring low-latency, scalable APIs and multi-step workflows.
A1 is building a proactive smart assistant for everyday users. We seek a Backend Engineer, AI, who owns inference and orchestration layers that power AI interactions, ensuring low latency, reliability, and scalable APIs used across mobile and desktop clients.
You will design inference pipelines, manage routing and caching, and optimize throughput and cost while handling multi-step workflows and external tool calls. Collaboration with ML and product teams is essential.