Staff DevOps Engineer

As a Staff DevOps Engineer, you will own the reliability and scalability of the infrastructure behind our production products, including speech APIs, real-time streaming services, and voice AI platforms. You will be deeply involved in high-impact projects across the company.

This means hands-on work on highly available production systems on AWS, Azure, Google Cloud and on-prem, and leading architecture decisions for multi-region, multi-cloud and private cloud deployments. You will work closely with engineering, SDK and product teams.

What you’ll do

• Work on the reliability of core production services end-to-end, with the goal of delivering and maintaining a 99.9% SLA
• Design and lead infrastructure architectures for multi-region, multi-cloud and private cloud / on-premise deployments for enterprise customers
• Design and build failover mechanisms, including auto-failover between regions and cloud providers
• Build monitoring, alerting and observability tooling that helps us detect issues fast, support incident management, and keep historical monitoring data
• Improve stability and latency of real-time streaming services (WebSocket-based), and optimize network cost and latency across regions
• Own deployment of new ML models and new product features to production together with engineering teams
• Participate in and lead production incident response, root cause analysis, and post-incident improvements
• Design, implement and maintain CI/CD pipelines (Jenkins, GitHub Actions)
• Manage patching and security across systems, and integrate security tools into our infrastructure
• Drive DevOps best practices, standards and documentation across the team.

What we are looking for

Must-have

• 5+ years of hands-on DevOps experience, including ownership of highly available production systems
• Proven experience designing and operating systems with strict SLA requirements (99.9% or higher)
• Deep production experience with Kubernetes (EKS preferred) and containers, including migrations from other orchestration platforms
• Strong experience with at least one major cloud provider (AWS preferred); experience with multi-region and multi-cloud architectures
• Hands-on experience with Infrastructure-as-Code tools (Terraform and/or Ansible)
• Experience designing CI/CD pipelines with Jenkins and GitHub Actions
• Strong experience with monitoring and observability stacks (Prometheus, Grafana, or similar) and incident management processes
• Solid fundamentals in networking (TCP/IP, DNS, load balancing, VPNs, firewalls, CDN)
• Strong Linux system administration skills
• Proficiency with scripting languages (bash, Python, or similar) for automation
• Strong proficiency in using Claude Code and AI-assisted coding workflows.

Nice-to-have

• Experience with private cloud or on-premise deployments for enterprise customers
• Experience with real-time / low-latency streaming systems (WebSocket, WebRTC, gRPC)
• Experience deploying and serving ML models in production (GPU workloads, inference platforms)
• Experience with network cost optimization in cloud environments.