Chai Research
Backend: AI Infra and GPU Orchestration
Palo Alto, CA · Full-time · Posted Oct 30, 2026
About the job
Build and operate backend infrastructure for model serving, inference, and GPU orchestration.
What you'll do
- Develop model-serving and inference infrastructure.
- Schedule and orchestrate GPUs across providers.
- Improve scaling, reliability, and cost efficiency.
Tools
Python, vLLM, SGLang, Docker, Kubernetes
AI focus
Build infrastructure for serving and running AI models, including inference and GPU scheduling.
Model-written summary · the original posting is authoritative