Senior SRE, MLOps & AI Infra Architect

Tiger Analytics; Washington; Hybrid; USD 100,000 - 140,000; Full time

Job summary

Tiger Analytics is seeking a Site Reliability Engineer (SRE) to maintain and ensure the reliability of our production AI platforms. The role requires expertise in Kubernetes, MLOps, and automation tools like Terraform. You will define and monitor service level objectives, architect scalable solutions, and play a crucial part in performance engineering for AI services. This hybrid position provides significant career development opportunities in a fast-growing environment.

Qualifications

• Experience in reliability and performance engineering, particularly with AI/ML services.
• Familiarity with automation tools for infrastructure management.
• Strong background in networking and cloud architectures.

Responsibilities

• Define, monitor, and maintain SLOs for AI/ML services.
• Architect auto-scaling strategies for Kubernetes.
• Ensure high availability of Vertex AI endpoints.

Skills

Kubernetes (GKE)

Python

Terraform

MLOps

CI/CD

Grafana

Prometheus

Tools

Vertex AI

Kubeflow

Google Cloud Operations Suite (Stackdriver)

Job description

Tiger Analytics is seeking a Site Reliability Engineer (SRE) to maintain and ensure the reliability of our production AI platforms. The role requires expertise in Kubernetes, MLOps, and automation tools like Terraform. You will define and monitor service level objectives, architect scalable solutions, and play a crucial part in performance engineering for AI services. This hybrid position provides significant career development opportunities in a fast-growing environment.