Search by job, company or skills

T

AI Platform Operations Engineer (Offshore)

7-13 Years
Save
  • Posted 15 hours ago
  • Be among the first 10 applicants
Early Applicant
Quick Apply

Job Description

We're Hiring: AI Platform Operations Engineer (Offshore)

Client: SAP SE

Location: Offshore (Remote)

⚡ Required Experience: 7+ years

Work Schedule: CET Time Zone (12:30 PM IST onwards)

⚡ Joining: Immediate Joiners Only

Are you passionate about operating and scaling enterprise AI platforms We're looking for an experienced AI Platform Operations Engineer to own observability, CI/CD, performance testing, and operational excellence for mission-critical AI services.

Key Responsibilities

Own and manage self-hosted Langfuse deployments on SAP BTP Kyma, including production migrations and LLM observability.

Configure and optimize Dynatrace monitoring, dashboards, alerts, and automated reporting for AI production services.

Build, maintain, and troubleshoot GitHub Actions CI/CD pipelines, branch protection rules, and deployment gates.

Design and execute K6 load testing frameworks for AI use cases, ensuring performance and reliability before production releases.

Maintain operational excellence through Jira backlog management, incident tracking, and runbook governance.

Debug and resolve operational issues in Python, ensuring pipeline and monitoring reliability.

Required Skills

️ Self-hosted Langfuse or equivalent LLM observability platforms

️ Dynatrace monitoring and alert management

️ GitHub Actions CI/CD pipeline development and administration

️ K6 load testing and performance analysis

️ Strong Python troubleshooting skills

️ SAP BTP, Kyma, Cloud Foundry, Kubernetes, and Helm fundamentals

️ Experience managing production incidents and operational workflows using Jira

Preferred Skills

Prometheus or similar metrics stacks

SAP BTP Object Store, PostgreSQL, and Redis

ServiceNow or enterprise ITSM platforms

We're Looking For Candidates Who:

Have owned observability for live AI or data platforms

Can identify and resolve LLM trace issues independently

Have implemented CI/CD quality gates that prevent production failures

Are comfortable interpreting operational metrics and configuring alerts without developer dependency

Not a Fit If You Are:

• A general DevOps engineer without AI/ML tooling experience

• A developer with limited production operations ownership

• A GUI-only platform administrator with no scripting expertise

Mandatory Requirements

• Must have an own laptop

• Must be available to work in the CET time zone

• Only genuine, real-time candidates with verified experience will be considered

• Recruiters must validate candidates thoroughly before submission

• LinkedIn profile, full date of birth, and last 4 digits of Aadhaar are required at the time of submission

More Info

Function:
Employment Type:

About Company

Job ID: 149307299