Description

Support production stability and observability for GenAI and predictive AI workloads.

This role is on-site.

Responsibilities

• Troubleshoot issues across data ingestion, model inference, and deployment layers.
• Define and implement observability strategies to monitor model failures, latency, and system health.
• Manage on-call rotations for GenAI and predictive pipelines one week every 6–8 weeks.
• Maintain enterprise disaster recovery solutions, including backup and restore processes.
• Support the full AI lifecycle from data pipelines to model deployment.

Required Skills

• 5+ years of experience in technical support or platform engineering roles.
• Hands-on experience with Elasticsearch or similar vector databases, including similarity search and indexing.
• Proficiency in Python for automation, data pipelines, and OpenAI integrations.
• Strong Linux command-line skills, shell scripting, and system-level debugging.
• Experience supporting predictive AI workloads in production environments.
• Familiarity with Docker, Kubernetes, and CI/CD pipelines.
• Knowledge of Hadoop-based platforms such as MapR or Hortonworks.
• Experience with observability tools like Splunk, Grafana, ELK stack, or OpenTelemetry.

Preferred Skills

• Exposure to GCP and Azure multi-cloud environments.
• Knowledge of MLOps principles and the full data science lifecycle.

Key Skills

Education

Any Graduate