Backend Engineer, AI (Agent Systems)

Overview

Build and operate the inference and orchestration layer behind production AI interactions. The role focuses on reliable, observable APIs and backend systems for AI-powered features.

What you'll do

• Build backend systems serving AI-powered features in production.
• Design inference pipelines and orchestration layers around models.
• Define service boundaries around AI models.
• Monitor, log, and alert on production systems.
• Respond to production incidents.
• Optimize latency and throughput through inference, caching, batching, and streaming.

What you'll need

• Strong backend engineering fundamentals in production environments.
• Experience running high-throughput, low-latency services.
• Familiarity with AI inference patterns, including LLMs, embeddings, and multimodal systems.
• Ability to debug distributed systems under load.
• Ability to execute independently and exercise judgment.
• Experience with Python, Node.js, PyTorch, SQL, NoSQL, Kubernetes, and Docker.

Details

• Location: China.
• Interviews may be conducted virtually and/or onsite.