Summary

The backend engineer will build SpaceXAI’s API and high-throughput inference infrastructure for serving AI models to developers. The role focuses on distributed systems, model serving, and scalable API services.

Responsibilities

• Build the API serving models to developers
• Operate high-throughput, low-latency inference systems
• Develop model serving and request routing
• Build SDKs and implement rate limiting
• Improve observability and scale infrastructure efficiently