Job Description

Job Summary

Job Description: AI Developer – Production Support Automation

Position: AI Developer – Production Support Automation

Experience: 5-10 Years

Location: Miami /Texas

Department: Production Support / Managed Services / Digital Operations

Role Summary

We are seeking an experienced AI Developer to drive automation and intelligence across Production Support operations. The role focuses on leveraging AI, Generative AI, Machine Learning, and automation technologies to reduce incident resolution time, improve operational efficiency, proactively identify issues, and minimize manual support efforts.

The ideal candidate will build AI-powered solutions for incident management, root cause analysis, ticket automation, knowledge management, and predictive monitoring in enterprise environments.

Key Responsibilities

• Design and develop AI-driven automation solutions for Production Support activities.
• Build intelligent systems for incident categorization, assignment, prioritization, and resolution recommendations.
• Develop GenAI-powered support assistants and virtual agents for L2/L3 support teams.
• Implement AI solutions for log analysis, anomaly detection, and predictive monitoring.
• Create automated Root Cause Analysis (RCA) frameworks using AI and Machine Learning.
• Develop Retrieval-Augmented Generation (RAG) solutions utilizing operational knowledge bases, runbooks, and support documentation.
• Integrate AI capabilities with ITSM platforms such as ServiceNow, Jira, Remedy, or similar tools.
• Build dashboards and insights for incident trends, SLA risks, and operational health monitoring.
• Collaborate with Production Support, Infrastructure, Network, Application, and Business teams to identify automation opportunities.
• Ensure compliance with security, governance, and Responsible AI standards.

Skill Requirements

AI / Generative AI

• OpenAI / Azure OpenAI
• LangChain / LangGraph
• Prompt Engineering
• RAG Architecture
• AI Agents and Agentic Workflows
• LLM Evaluation and Guardrails

Programming

• Python (Mandatory)
• REST APIs
• FastAPI / Flask
• Shell Scripting

Data & Analytics

• Pandas
• NumPy
• SQL
• Vector Databases (FAISS, ChromaDB, Pinecone)

Machine Learning

• Anomaly Detection
• Predictive Analytics
• Classification Models
• NLP Techniques

Monitoring & Support Tools

• Splunk
• Dynatrace
• AppDynamics
• ELK Stack
• Grafana
• Prometheus

ITSM Platforms

• ServiceNow
• Jira Service Management
• BMC Remedy

Cloud & DevOps

• Azure / AWS
• Docker
• Kubernetes
• GitHub Actions
• CI/CD Pipelines

Key Automation Use Cases

• Incident Auto-Triage
• AI-based Ticket Summarization
• Auto RCA Generation
• Knowledge Article Creation
• Alert Noise Reduction
• Predictive Incident Detection
• Production Health Monitoring
• AI-powered Runbook Execution
• MTTR Reduction Initiatives
• L1/L2 Support Chatbots

Required Experience

• 5+ years in Application Production Support, SRE, DevOps, or Automation.
• 2+ years of hands-on experience in AI/GenAI solution development.
• Experience working with enterprise support environments and ITIL processes.
• Strong exposure to monitoring, logging, and operational support ecosystems.

Preferred Qualifications

• Experience in Telecom, Retail, Banking, or Enterprise Support Operations.
• Azure AI Engineer, AWS AI, ServiceNow, or ITIL certifications.
• Experience building AI solutions for large-scale production environments.

Success Metrics

• Reduction in MTTR (Mean Time to Resolution)
• Reduction in Manual Support Efforts
• Ticket Deflection Rate
• Automation Coverage %
• SLA Compliance Improvement
• Operational Cost Savings
• Proactive Incident Identification Rate

Business Impact Statement

Drive AI-led transformation of Production Support operations by automating incident management, accelerating root cause identification, improving system reliability, reducing operational costs, and enabling support teams to focus on high-value business-critical activities.

This JD is aligned for AI-led Production Support Automation programs in large enterprises such as Verizon, telecom, and managed services environments, where the focus is on reducing support effort, improving SLA adherence, and increasing operational efficiency.

Other Requirements