Specialist - System Management

LTM Inc

• $110K — $130K *
Information Technology
11 - 15 years of experience
Job Overview by Ladders

Qualifications

  • 12 years of experience in application production support for AILLM-based applications
  • Strong knowledge of API performance and troubleshooting in production environments
  • Hands-on experience with Redis and MongoDB databases
  • Proficient in monitoring and troubleshooting using Splunk and Dynatrace
  • Experience with containerization technologies like Kubernetes and OpenShift
  • Familiarity with LLM observability platforms such as Galileo and LangSmith
  • Basic knowledge of VMware environments

Responsibilities

  • Provide Level 2 and Level 3 support for applications using LLM Generative AI models
  • Troubleshoot API performance issues and production problems related to AILLM workloads
  • Monitor and analyze system performance using Splunk and Dynatrace
  • Manage and optimize containerized applications with Kubernetes or OpenShift
  • Utilize observability tools for LLM development and performance insights
  • Conduct root cause analysis for incident management
  • Collaborate in an agile environment to ensure application reliability and efficiency

Benefits

  • Collaborative and innovative work environment
  • Opportunities for professional development and continuous learning
  • Access to cutting-edge technology and tools
  • Flexible work arrangements
  • Strong emphasis on work-life balance
Full Job Description
Role description

We are looking for an Application Production Support Engineer with 12 years of experience supporting AILLMbased applications in a production environment

Key Responsibilities Skills

Provide L2L3 production support for applications leveraging LLMGenerative AI models

Troubleshoot application API performance and production issues related to AILLM workloads

Experience with Redis and MongoDB databases

Monitoring and troubleshooting using Splunk and Dynatrace

Experience with containerized applications using Kubernetes andor OpenShift

Exposure to Galileo and LangSmith or similar LLM observabilitydevelopment platforms

Understanding of LLM tokens Tokens Per Minute TPM Requests Per Minute RPM throttling and rate limits

Basic understanding of VMware environments

Strong incident management troubleshooting rootcause analysis and production support skills

Preferred Profile Application Support professionals with handson exposure to AILLM projects rather than pure AIML developers

Similar Jobs

More Jobs at LTM Inc

More Information Technology Jobs

Find similar Specialist - System Management jobs: