REMOTE Security Platform Operations Engineer I (AI...

This role is specifically responsible for the day-to-day operation of an LLM-based code vulnerability detection and reporting capability. The primary focus is run: monitoring, executing runbooks, patching, and resolving defects in the deployed scanner and its pipelines. The role contributes to build and feature work under direction from Lead and Principal Engineers, but is not responsible for solution design. This position is one of four engineers providing rotating coverage for a 24/7 operational capability. Scheduled hours average 40 per week, and alert volume is expected to be low, so shift time not spent on active response is directed toward maintenance, documentation, and assigned engineering tasks. Finding triage and remediation ownership are out of scope for this role., 1. Operate and monitor an LLM-based code vulnerability detection capability on AWS Bedrock, including scanner health, job execution, model invocation errors, and token and cost consumption against defined thresholds.

1. Monitor scanning pipelines integrated with GitHub and Jenkins running on ECS; investigate and resolve failed jobs, queue backlogs, and environment issues.

2. Execute documented runbooks during assigned shift and escalate to Lead or Principal Engineering per established procedures.

3. Perform structured shift handoff, including documentation of open issues, in-flight changes, and outstanding escalations.

4. Apply patches, dependency updates, and configuration changes through established change management processes.

5. Monitor Splunk dashboards and alerts for scanner health, coverage, and throughput; report anomalies and recurring failure patterns.

6. Execute the evaluation harness on a defined cadence and report results; identify regressions in detection performance.

7. Implement assigned changes at the Story level within an established architecture, including Terraform and pipeline configuration updates.

8. Maintain and improve runbooks, operational procedures, and support documentation based on observed incidents.

9. Participate in a four-person rotating shift schedule providing 24/7 coverage, including nights, weekends, and holidays. Scheduled hours average 40 per week.

10. Maintain appropriate controls and documentation to ensure compliance with all company and regulatory requirements.

11. Understand virtualization/containerization technologies.

12. Other duties as assigned.

• 1+ years of related engineering or technical operations experience, including hands-on information security, infrastructure, or software support work.

• 1+ year of Gen AI related development

• Working knowledge of AWS fundamentals, including console and CLI navigation, IAM basics, and CloudWatch.

• Ability to read and troubleshoot CI/CD pipeline failures, preferably Jenkins, integrated with GitHub.

• Ability to read and make guided modifications to Terraform and scripting in Python or equivalent.

• Basic understanding of application security concepts and common vulnerability classes. · Prior experience supporting a 24/7 operational environment, including shift handoff and runbook execution.

• Exposure to AWS Bedrock or equivalent hosted LLM platforms.

• Hands-on experience with ECS or other container orchestration platforms.

• Splunk experience, including search and dashboard use.

• Experience with Linux systems administration.

• Experience working with ServiceNow or equivalent incident and change management tooling.

• Experience working in Agile methodologies.

• Prior experience in a regulated financial services environment.

• Industry standard certifications such as AWS Cloud Practitioner, AWS Solutions Architect Associate, or CompTIA Security+.