AI Platform Engineer – OneAI

About the role

OpenNebula Systems is looking for an AI Platform Engineer to join its fully‑remote, international team. You will help build OneAI, a high‑performance platform that runs inference and training workloads across cloud and edge environments.

Key responsibilities

• Design, implement and deploy advanced AI capabilities within the OneAI platform.
• Integrate AI frameworks and engines such as vLLM, PyTorch and Unsloth into a secure, scalable, and observable architecture.
• Provision compute resources, schedule workloads and expose reliable APIs for the full AI model lifecycle.
• Develop intuitive user workflows for model management, deployment configuration and job operation.
• Connect with public model repositories like Hugging Face to enable seamless model discovery, versioning and deployment.
• Establish deployment strategies, optimise performance and cost, and implement GPU‑aware operations.
• Build observability tools to monitor latency, throughput, utilisation and failure rates.

Required profile

• Strong background in applied AI, systems engineering and product design.
• Experience working on cloud and edge computing platforms.
• Ability to work independently in a distributed, remote environment.
• Fluent English for communication and CV submission.

Required skills

• vLLM
• PyTorch
• Unsloth
• Hugging Face model repositories
• OpenNebula cloud management platform
• API design and implementation
• GPU‑aware workload orchestration
• Observability and monitoring tools