AIOps

Job Description:

Job Description - JR

Job Description Date: August 2026

Role : AI Operations & Automation Specialist

Number of positions : 1

Description:

We are seeking a hands-on highly technical AI Operations & Automation Engineer with around 2 years of experience to join our centralized AI Product Support & Operations team. Reporting directly to the Senior AIOps Lead you will serve as the hands-on technical builder responsible for executing automation pipelines integrating intelligent tools and building data-driven systems across our AI product ecosystem.

In this role your primary mission is to write code connect APIs deploy RAG-driven knowledge tools and build operational dashboards under the guidance of the Senior AIOps Lead. You will work closely with L1/L2 support teams to eliminate manual workflows automate ticket triage and build automated diagnostic mechanisms that drive down Mean Time to Resolution (MTTR).

Qualification & Experience:

Education: Bachelors or Masters degree in Computer Science Information Technology Software Engineering or a related quantitative field.

Experience: 2 years of hands-on experience in Software Engineering AIOps DevOps Systems Automation or Technical Support Engineering.

Key Responsibilities

• Build test and deploy automated scripts (Python Shell or PowerShell) and API integrations under the direction of the Senior AIOps Lead to streamline operational processes.

• Develop and maintain RAG-based (Retrieval-Augmented Generation) search tools and LLM utilities that index historic tickets logs and root-cause analyses (RCAs) so L1/L2 engineers can instantaneously surface past fixes.

• Implement conversational AI bots webhooks and self-service automation workflows within our ticketing portals to auto-resolve routine Tier-1 inquiries.

• Construct and customize automated dashboards (e.g. ServiceNow) to provide real-time visual metrics on system uptime ticket velocity MTTR SLA compliance and CSAT.

• Implement automated log-scraping and context-enrichment scripts that pre-fetch relevant telemetry data and append it directly to incoming support tickets upon creation.

• Pair with L1/L2 support engineers to identify repetitive manual tasks converting friction points into single-click scripts or auto-remediation triggers.

• Help structure log outputs and standardize ticket tags to ensure incident history remains clean searchable and machine-readable.

• Assist the Senior AIOps Lead in configuring real-time alert triggers and predictive anomaly detection models across cloud infrastructure.

• Run automated stress-test scripts and assist with validating self-healing infrastructure routines for recurring platform errors.

• Scripting & Coding: Strong proficiency in Python or Shell scripting for building micro-automation tasks log parsing and utility tooling.

• APIs & Data Pipelines: Direct hands-on experience connecting REST APIs webhooks JSON parsers and data ingestion workflows.

• AI/LLM Utilities: Practical experience using LLM APIs vector databases or basic RAG architectures for text/document search and classification.

• ITSM & Visualization: Working knowledge of ITSM platforms (Jira Service Management ServiceNow) alongside visualization platforms (Looker Studio).

• Cloud Environments: Base-level understanding of cloud infrastructure (AWS Azure or GCP) microservice architectures and system telemetry logs.

• Builder Mentality: Relentless focus on solving operational bottlenecks with clean maintainable code rather than temporary manual workarounds.

• Technical Agility: High adaptability to rapidly test iterate and refine scripts based on feedback from the Senior AIOps Lead and support engineers.

• Structured Problem Solving: Strong ability to trace software errors read stack traces and translate raw system logs into clear operational metrics.

• Prior exposure to LLM framework engineering (e.g. Lang Chain Llama Index or Anthropic APIs).

• Certifications: AWS/GCP Certified Developer/SysOps or Python certifications.

• Familiarity with SQL vector search or log management engines.

• MTTR Reduction: Lowering resolution times through automated diagnostics and fast access to prior solution data for L1/L2 teams.

• Ticket Deflection Rate: Measurable percentage of Tier-1 issues resolved automatically via self-service and bot interventions.

• Dashboard Accuracy & Coverage: Comprehensive real-time visual tracking of all core metrics (Uptime MTTR CSAT Ticket Trends).

• L1/L2 Productivity: Reduction in manual triage time and repetitive tasks across the support organization

This job requires an awareness of any potential compliance risks and a commitment to act with integrity as the foundation for the Companys success reputation and sustainable growth.

Company:

Employment Type:

-------

Experience Level:

Job Family: