SRE Engineer with ML Ops and Arize product

Tittle – SRE Engineer with ML Ops and Arize product

Location – Malvern, PA - 100% ONSITE FROM DAY 1

 

ROLE_DESCRIPTION -

AWS Cloud Platform Expertise - EC2, EKS, ECS, Lambda, CloudWatch, SNS, SQS, Event Bridge for highly available and scalable services.

Arize AI Observability & Monitoring - Model performance monitoring, drift detection, evaluation analytics, and AI/LLM observability.

Site Reliability Engineering (SRE) - SLI/SLO definition, Error Budgets, reliability improvement, service resilience, and uptime management.

Incident Management & RCA - Major Incident Management (MIM), outage tracking, root cause analysis, problem management, and MTTR reduction.

Failure Analysis & Risk Assessment - FMEA, risk quantification, reliability assessments, and proactive mitigation of platform failures.

Testing & Validation Engineering - Scenario testing, regression testing, impact analysis, release validation, and upstream change testing.

Monitoring, Alerting & Automation - CloudWatch, Grafana, Prometheus, PagerDuty, automated notifications, dashboards, and operational metrics.

DevOps & MLOps Practices - Kubernetes, Terraform, CI/CD pipelines, Python scripting, AI/ML platform operations, and LLM reliability optimization.

Preferred Technologies: AWS, Arize AI, Kubernetes (EKS), CloudFormation, Python, CloudWatch, Grafana, Prometheus, PagerDuty, GitHub Actions/Jenkins.

SYSMIND LLC is an Equal Employment Opportunity employer. All qualified applicants will receive consideration for employment without any discrimination. We promote and support a diverse workforce at all levels in the company. All job offers are contingent upon completion of a satisfactory background check and reference checks. Additionally passing the drug test may also be required. All contractors intending to work on SYSMIND's W2 are "at will" employees.