Application Production Support Engineer – AI/LLM

Tasks

• Provide L2/L3 production support for Generative AI and LLM-based applications.
• Monitor application health, performance, and availability using Splunk and Dynatrace.
• Troubleshoot issues involving AI applications, APIs, backend services, infrastructure, and databases.
• Manage incidents, perform Root Cause Analysis (RCA), and resolve issues within SLA timelines.
• Support and maintain Redis and MongoDB databases.
• Monitor LLM metrics, including token usage, TPM, RPM, throttling, and rate limits.
• Support containerized applications running on Kubernetes and/or OpenShift.
• Work with LLM observability tools such as LangSmith, Galileo, or similar platforms.
• Collaborate with development, cloud, infrastructure, and AI engineering teams.
• Participate in deployments, release management, and change management activities.
• Maintain operational runbooks, troubleshooting guides, and knowledge-base documentation.

Requirements

• 8+ Years
• Application Production Support (L2/L3)
• Generative AI / Large Language Models (LLMs)
• Splunk / Dynatrace
• Redis / MongoDB
• Kubernetes / OpenShift
• Incident Management / RCA / SLA
• LLM Observability: LangSmith / Galileo

Schedule

• Hybrid – 3 Days/Week Onsite

How to apply

• Share your updated resume via DM or email.

Location

• Charlotte, NC