AI Engineer (Python/LangGraph/Agentic AI)

Overview:

Design and implement innovative observability and automation solutions, enhancing the demand for development resources within the Site Reliability Engineering (AIOps and Agentic AI) domain.

Primary Responsibilities:

AIOps & Agentic AI Development

• Create Python and/or LangGraph scripts along with agentic AI workflows to streamline operational processes, diagnostics, and remediation efforts.
• Establish and integrate AIOps functionalities for predictive alerting, anomaly detection, and intelligent event correlation across both infrastructure and applications.
• Design and implement agentic AI solutions that enhance incident response and minimize the need for manual intervention.
• Develop self-healing and auto-remediation workflows driven by AI/ML insights and event correlation data.

Infrastructure Automation and CI/CD

• Engineer infrastructure automation for the provisioning, configuration, and management of systems in a consistent and auditable manner.
• Oversee automation and AI code management via GitHub, employing version control, code review, and collaboration best practices.
• Incorporate AIOps and automation elements into CI/CD pipelines to facilitate continuous testing, validation, and deployment.

Observability, Reliability & Team Collaboration

• Implement observability and event correlation across metrics, logs, and traces to support proactive reliability management.
• Promote SRE frameworks and reliability practices, integrating AIOps into the delivery lifecycle.
• Work alongside Application, Infrastructure, Cloud, and Cyber teams to foster predictive incident prevention and root-cause transparency.
• Maintain comprehensive documentation and runbooks, while mentoring engineers on AIOps and automation best practices.