Staff DevOps Engineer | Hybrid - Full Time
Core
Own reliability and scalability of infrastructure for speech APIs, real-time streaming services, and voice AI platforms.
Role type
Staff DevOps Engineer (multi-cloud, high availability)
Builds
Highly available production systems, multi-region/multi-cloud architectures, CI/CD pipelines, observability tooling
Domain
Cloud Infrastructure, DevOps, Real-time Streaming, Voice AI
Deliverable
production ML models
Required skills
Kubernetes, AWS, Terraform, Ansible, Jenkins, GitHub Actions, Prometheus, Grafana, Linux, Networking (TCP/IP, DNS, Load Balancing), Bash, Python, AI-assisted coding workflows
Preferred skills
Private cloud/on-premise deployments, Real-time streaming (WebSocket, WebRTC, gRPC), ML model deployment (GPU workloads), Network cost optimization
Technologies
AWS, Azure, Google Cloud, Kubernetes (EKS), Jenkins, GitHub Actions, Terraform, Ansible, Prometheus, Grafana, WebSocket, WebRTC, gRPC
Responsibilities
Design and lead infrastructure architectures for multi-region, multi-cloud and private cloud deployments; Build failover mechanisms including auto-failover between regions and cloud providers; Design and build monitoring, alerting and observability tooling; Improve stability and latency of real-time streaming services; Own deployment of new ML models and new product features to production; Participate in and lead production incident response, root cause analysis, and post-incident improvements; Design, implement and maintain CI/CD pipelines; Manage patching and security across systems; Drive DevOps best practices, standards and documentation.
Seniority
Staff, hands-on IC with strategic leadership