R&D AI Platform Engineer / Administrator
Core
Design and deploy on-premises AI infrastructure to host open-source models and support internal AI platform services for Global R&D.
Role type
R&D AI Platform Engineer / Administrator
Builds
Secure, on-premises AI capabilities and scalable platform services for product development
Domain
Optical networks, routing, switching, network control systems, on-premises AI/ML
Deliverable
production ML models
Required skills
Kubernetes, Docker, Linux, LLM serving frameworks (SGLang, vLLM), orchestration layers (LiteLLM), vector databases (Milvus), observability solutions (Langfuse, Prometheus/Grafana), network security, container security, data privacy
Preferred skills
Atlassian tools (Jira, Confluence, Bitbucket), private cloud architectures (OpenStack), CI/CD pipeline environments
Technologies
Kubernetes, Docker, SGLang, vLLM, LiteLLM, Open WebUI, Milvus, Langfuse, Prometheus, Grafana, Oracle Linux, OpenStack
Responsibilities
Design and deploy on-premises AI infrastructure; Implement and manage model serving solutions; Configure and maintain AI application stack components; Ensure adherence to enterprise security policies; Collaborate with AI architects and product teams; Deliver documentation and guidance to internal users
Seniority
Mid-level, hands-on IC