SRE Engineer – MLOps & Arize AI

Location: Malvern, PA — 100% Onsite
Duration: 6 Months
Experience: 6–8 Years

Candidates with a combination of strong AWS SRE + MLOps + Arize AI/ML observability experience are strongly preferred.

Job Description

We are seeking an experienced SRE Engineer with strong MLOps and AI observability experience, particularly with Arize AI. The ideal candidate will have hands-on expertise in AWS, Kubernetes, monitoring, incident management, reliability engineering, and ML/LLM platform operations.

Must-Have Skills

• AWS: EC2, EKS, ECS, Lambda, CloudWatch, SNS, SQS, EventBridge
• Arize AI: AI/ML model monitoring, performance monitoring, drift detection, evaluation analytics, and LLM observability
• Strong SRE experience with SLI/SLO definition, error budgets, reliability engineering, resilience, and uptime management
• Kubernetes / EKS
• MLOps / ML platform operations
• Python scripting
• Monitoring and observability using CloudWatch, Grafana, and Prometheus
• Incident management, RCA, problem management, and MTTR reduction
• Terraform and infrastructure automation
• CI/CD pipelines using GitHub Actions or Jenkins.

Education & Experience

• 10 years of experience in SRE, DevOps, Cloud Engineering, MLOps, or related roles.
• Strong hands-on AWS cloud experience.
• Experience supporting AI/ML platforms and MLOps environments.
• Experience with Arize AI or comparable AI/ML observability platforms is highly preferred.
• Strong understanding of reliability engineering, monitoring, incident management, automation, and cloud-native technologies.
• Excellent troubleshooting, communication, and problem-solving skills.