Lead DevOps Engineer for Real-Time AI Infra Across 3 Clouds

Skit; Hinoba-an; On-site; PHP 1,500,000 - 2,600,000; Full time

Job summary

Skit.ai in the Philippines is seeking a Lead DevOps Engineer to own our multi-cloud, real-time media platform designed for regulated enterprises. You will shape architecture across AWS, GCP, and Azure, with self-hosted LiveKit and SIP, and GPU-based model serving to meet sub-500ms budgets.

You will drive reliability, observability, and security, mentor SREs, and push IaC-first standards across the team to sustain scale.

Qualifications

• 6+ years hands-on cloud infrastructure experience.
• 3+ years operating multiple clouds in production.
• Deep expertise in at least two of AWS/GCP/Azure.
• Real-time audio/video systems in production experience.
• Strong networking, VPC/VNet design and private connectivity.
• Kubernetes at scale with stateful workloads and service mesh.
• Terraform-based IaC across multi-account estates.
• AI/ML serving in production with GPU scheduling.
• Secure CI/CD with integrated security scanning.
• Production STT/TTS/LLM API operations knowledge

Responsibilities

• Own multi-cloud substrate across AWS, GCP, and Azure.
• Design real-time media plane with autoscaling and LiveKit/SIP.
• Manage GPU fleets for self-hosted ASR and open-weight LLMs.
• Establish reliability and observability with tracing and runbooks.
• Lead cost engineering to optimize per-minute serving costs.
• Enforce Zero Trust, IAM/RBAC, and auditable controls.
• Provide technical leadership and enforce IaC standards.

Skills

Cloud infrastructure

Multi-cloud production

Real-time media systems

Networking depth

Kubernetes at scale

Infrastructure as Code

AI/ML model serving

Streaming protocols

Security fundamentals

CI/CD pipelines

Tools

Terraform

Kubernetes (EKS/GKE/AKS)

Istio/Linkerd

LiveKit

WebRTC

Triton/vLLM

Job description

Skit.ai in the Philippines is seeking a Lead DevOps Engineer to own our multi-cloud, real-time media platform designed for regulated enterprises. You will shape architecture across AWS, GCP, and Azure, with self-hosted LiveKit and SIP, and GPU-based model serving to meet sub-500ms budgets.

You will drive reliability, observability, and security, mentor SREs, and push IaC-first standards across the team to sustain scale.