AI Backend Engineer: Low-Latency Inference Architect
Summary
Design and maintain the low-latency inference layer that powers AI features, turning models into fast, reliable APIs for clients using Python, Kubernetes, and LLMs.
Base Camp Digital is seeking an AI Backend Engineer to own the inference and orchestration layer powering AI features across the product. You will design, build, and operate production systems turning model capability into fast, reliable APIs used by mobile and desktop clients.
You will optimize latency, implement monitoring and incident response, and work with Python, Node.js, PyTorch, OpenAI/Anthropic/LLMs, SQL/noSQL, Kubernetes and Docker in a distributed, production environment.