Senior Site Reliability Engineer

What you'll do

• Own end-to-end service accountability for payer-focused AI, LLM, and ML-enabled platforms across hybrid environments.
• Oversee MLOps processes including model deployment, monitoring, retraining, validation, and rollback strategies.
• Coordinate the deployment and lifecycle management of containerized services using Kubernetes.
• Implement and govern Infrastructure as Code (IaC) practices using Terraform to manage cloud and on-premises resources.
• Standardize configuration management through Ansible automation to improve operational efficiency.
• Support the operational management of Node.js-based services and APIs that integrate AI capabilities.
• Lead incident management, root cause analysis, and service restoration activities to minimize business impact.
• Monitor platform health using metrics, logs, traces, and observability tools to improve service reliability.

What we're looking for

• Strong experience with Kubernetes and GCP (GKE).
• Strong experience in IaC (Terraform), Helm, and GitHub Actions.
• Proficiency in Python, Ansible, and Node.js.
• Strong experience with Prometheus and Grafana observability stack.
• Solid understanding of Linux systems and networking fundamentals.
• Experience in incident management, on-call support, and production triage.
• Hands-on experience with automation and CI/CD pipelines.
• Strong understanding of AI/ML concepts and AIOps practices.
• Candidate must be legally authorized to work in the United States without the need for employer sponsorship.
• Google Cloud Architect Certification (preferred).
• Certified Kubernetes Administrator (CKA) (preferred).
• Experience in Java/J2EE, Spring Boot (preferred).
• Experience supporting or operating ML/AI platforms or pipelines (MLOps) (preferred).
• Exposure to AIOps tools, anomaly detection, or predictive analytics systems (preferred).
• Experience with large-scale distributed systems and microservices architecture (preferred).
• Experience with GPU-based workloads or ML infrastructure on GCP (preferred).
• Knowledge of Kubeflow, Vertex AI, or ML pipelines (preferred).
• Experience integrating AI-driven automation into monitoring and incident response (preferred).