Site Reliability Engineer AI & Data Platforms (LLM & Kubernetes)

As an AI Support Engineer at Power Cozmo (India & Jordan), based in Amman, Jordan, you will play a crucial role in maintaining and supporting Kubernetes clusters for our production AI and data systems. Your responsibilities will involve a range of tasks related to infrastructure support, local LLM platform maintenance, data scraping, system monitoring, incident support, and automation.

Key Responsibilities:

• **Kubernetes & Infrastructure Support**
• Deploy, manage, and support production-grade Kubernetes clusters
• Troubleshoot pod, node, networking, and storage issues in live environments
• Manage Helm charts, ConfigMaps, Secrets, and Kubernetes manifests
• Manage infrastructure and application deployments via Git repositories
• **Local LLM & AI Platform Support**
• Support local LLM deployments (Ollama, Mistral, LLaVA, Qwen, etc.)
• Troubleshoot inference performance, memory issues, and model loading failures
• Support AI services exposed via REST APIs or internal microservices
• **Data Scraping & Crawling**
• Support and maintain web scraping and crawling pipelines
• Debug data extraction failures, rate limits, and anti-bot challenges
• Ensure data quality, consistency, and pipeline reliability
• Assist in scheduling and monitoring crawlers (cron jobs)
• **System Monitoring & Incident Support**
• Perform root cause analysis for production incidents
• Monitor logs, metrics, and alerts using tools like Prometheus, Grafana
• Maintain uptime and SLAs for AI and data platforms
• Participate in on-call or escalation support rotations
• **Automation**
• Maintain documentation for support procedures and known issues
• Collaborate with engineering teams for fixes and optimizations

Required Skills & Qualifications:

• 5+ years experience as a Data / AI Support Engineer
• Hands-on experience with Docker and containerized workloads
• Experience supporting local LLM models or AI inference systems
• Practical knowledge of Linux system administration
• Experience with data scraping or web crawling systems
• Basic scripting skills (Python, Bash)

Preferred / Good to Have:

• Familiarity with Neo4j, Kafka, or data pipelines
• Experience with Ollama, Hugging Face models, or similar LLM runtimes
• Knowledge of cloud-native monitoring tools
• Understanding of networking concepts (DNS, ingress, load balancers)

In this role, you will have the opportunity to work on cutting-edge AI and LLM infrastructure both over the cloud and local AI servers in a fast-paced startup or scale-up environment, offering significant career growth opportunities in the field of AI. As an AI Support Engineer at Power Cozmo (India & Jordan), based in Amman, Jordan, you will play a crucial role in maintaining and supporting Kubernetes clusters for our production AI and data systems. Your responsibilities will involve a range of tasks related to infrastructure support, local LLM platform maintenance, data scraping, system monitoring, incident support, and automation.

Key Responsibilities:

• **Kubernetes & Infrastructure Support**
• Deploy, manage, and support production-grade Kubernetes clusters
• Troubleshoot pod, node, networking, and storage issues in live environments
• Manage Helm charts, ConfigMaps, Secrets, and Kubernetes manifests
• Manage infrastructure and application deployments via Git repositories
• **Local LLM & AI Platform Support**
• Support local LLM deployments (Ollama, Mistral, LLaVA, Qwen, etc.)
• Troubleshoot inference performance, memory issues, and model loading failures
• Support AI services exposed via REST APIs or internal microservices
• **Data Scraping & Crawling**
• Support and maintain web scraping and crawling pipelines
• Debug data extraction failures, rate limits, and anti-bot challenges
• Ensure data quality, consistency, and pipeline reliability
• Assist in scheduling and monitoring crawlers (cron jobs)
• **System Monitoring & Incident Support**
• Perform root cause analysis for production incidents
• Monitor logs, metrics, and alerts using tools like Prometheus, Grafana
• Maintain uptime and SLAs for AI and data platforms
• Participate in on-call or escalation support rotations
• **Automation**
• Maintain documentation for support procedures and known issues
• Collaborate with engineering teams for fixes and optimizations

Required Skills & Qualifications:

• 5+ years experience as a Data / AI Support Engineer
• Hands-on experience with Docker and containerized workloads
• Experience supporting local LLM models or AI inference systems
• Practical knowledge of Linux system administration
• Experience with data scraping or web crawling systems
• Basic scripting skills (Python, Bash)

Preferred / Good to Have:

• Familiarity with Neo4j, Kafka, or data pipelines
• Experience with Ollama, Hugging Face models, or similar LLM runtimes
• Knowledge of cloud-native monitoring tools
• Understanding of networking concepts (DNS, ingress, load balancers)