DevOps - AI Factory
Core
Design and operate distributed AI production systems at very high scale, focusing on quality, robustness, and reliability for Kaltura's video platform.
Role type
Senior DevOps & Platform Engineer (AI Factory)
Builds
Distributed AI production systems, GPU inference platforms, and resilient infrastructure on AWS and GCP.
Domain
Cloud Infrastructure, AI/ML Operations, Video Technology
Deliverable
production ML models
Required skills
Kubernetes internals, GPU inference (vLLM/SGLang/Nvidia Triton), multicloud infrastructure (AWS/GCP/NeoClouds), Infrastructure as Code (Terraform), CI/CD automation, observability (Prometheus/Grafana), Linux networking, AI coding tools
Preferred skills
AI evals and observability (Opik/OpenEval/LangSmith)
Technologies
AWS, GCP, NeoClouds, Kubernetes, Helm, Docker, Terraform, GitHub Actions, Prometheus, Grafana, vLLM, SGLang, Nvidia Triton, KubeFlow, Ray
Responsibilities
Lead initiatives end-to-end from design to production rollout; Design, build, and operate highly available distributed systems at scale; Build and operate infrastructure for AI workloads including GPU inference; Drive system reliability, monitoring, and observability; Collaborate with AI/ML Researchers and Product teams to translate needs into resilient systems.
Seniority
Senior, hands-on IC
