R&D AI Platform Engineer / Administrator
On-site · Ottawa, Ontario, Canada
Job Summary
Design and deploy on-premises AI infrastructure using Kubernetes and Docker to host open-source models and support AI-for-engineering initiatives. Implement and manage model serving with SGLang or similar, orchestration with LiteLLM, and vector databases like Milvus. Configure AI application stack components including LiteLLM, Open WebUI, Milvus, and Langfuse; ensure compliance with enterprise security policies and governance standards. Collaborate with AI architects and product teams to identify requirements and deliver scalable platform capabilities; produce documentation and guidance to enable internal users to effectively utilize AI platform services.
Required Qualifications
- 3+ years of experience developing and administering on-premises AI/ML platforms
- Experience with Kubernetes, Docker, and Linux environments
- Application of LLM serving frameworks such as SGLang or vLLM, orchestration layers including LiteLLM, and vector databases such as Milvus
- Implementation of observability solutions for AI workflows including Langfuse or Prometheus/Grafana
- Application of network security, container security, and data privacy practices in enterprise environments
- Ability to translate technical constraints into business-aligned outcomes for stakeholders
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.