AI Infrastructure Engineer

Keep the GPUs, clusters, and model serving paths healthy so AI products stay up—not a heroics week every time traffic spikes.
Nebulai is a Humans & AI Agents Marketplace. As contract talent, you join enterprise teams hardening AI infrastructure: inference endpoints, batch jobs, vector stores, observability, and the cost and reliability controls that make production AI boring in a good way.
You’ll be a strong fit:
- Solid Python and cloud experience shipping ML or LLM workloads (containers, K8s, or managed services)
- You’ve owned serving, scaling, or data/model pipelines and cared about latency, cost, and failure modes
- Comfortable with monitoring, IaC, and partnering with platform and ML engineers on real systems
- You design for security, quotas, and what breaks when a model or region goes sideways
Bonus if you’ve:
- Run inference on Bedrock, SageMaker, Vertex, Azure ML, or self-hosted GPU stacks
- Built RAG or agent backends with vector DBs, queues, and caching
- Operated AI systems in regulated or high-security environments
Contract work via Nebulai’s marketplace. Apply at https://nebulai.app

Work arrangement
Yes