AI/LLM Engineer I

We are seeking a skilled and proactive Apollo L1 Support Engineer to join our AI Platform Operations team. In this role, you will serve as the first line of technical support for our AI/LLM platform, providing expert-level troubleshooting and incident resolution for complex technical issues involving APIs, networking, and Python-based applications.

This is a highly technical support role requiring strong developer skills and a deep understanding of IT infrastructure. You will work closely with development teams, platform engineers, and end-users to ensure the reliability and performance of our AI platform.

Key Responsibilities

Technical Support & Incident Management

• Incident Handling:Receive, triage, and resolve Level 1 technical incidents related to the Apollo AI platform, ensuring timely resolution and minimal service disruption.
• API Troubleshooting:Diagnose and resolve API connectivity, authentication, and performance issues using tools like Postman, curl, and logging platforms.
• Networking Support:Troubleshoot network-related issues including connectivity, latency, DNS, and firewall configurations affecting platform access.
• Python Application Support:Debug and resolve issues with Python-based automation scripts, data pipelines, and integration workflows.

System Monitoring & Operations

• Proactive Monitoring:Monitor platform health and performance using observability tools, identifying potential issues before they impact users.
• Alert Response:Respond to system alerts, perform initial diagnostics, and escalate complex issues to Level 2/3 engineers as needed.
• Runbook Execution:Follow documented runbooks and standard operating procedures for incident resolution and system maintenance tasks.

Documentation & Knowledge Management

• Knowledge Base:Create and maintain detailed documentation, knowledge articles, and troubleshooting guides to support end-users and internal teams.
• Incident Reports:Document incident root causes, resolution steps, and preventive measures to build a comprehensive knowledge repository.
• Continuous Improvement:Contribute to the improvement of support processes, runbooks, and automation scripts.

Collaboration & Communication

• Cross-functional Collaboration:Work closely with development, platform engineering, and product teams to resolve complex technical issues and communicate platform updates.
• Stakeholder Communication:Provide clear and professional updates to stakeholders on incident status, resolution timelines, and root cause analysis.
• Knowledge Sharing:Actively participate in knowledge transfer sessions, team stand-ups, and post-incident reviews.

Escalation & Incident Management

• Escalation:Escalate complex or unresolved issues to Level 2/3 engineers with clear documentation and diagnostic information.
• Triage & Prioritization:Prioritize incidents based on business impact and service level agreements (SLAs), ensuring critical issues are addressed immediately.
• Incident Documentation:Ensure accurate and detailed logging of all incidents and service requests in the ticketing system.

What do you need to succeed

• Bachelor's degree in Computer Science, Information Technology, Engineering, or a related field.
• 3+ yearsof experience in a technical support, software development, or systems engineering role.
• Proven experience troubleshooting complex technical issues in a production environment.

Technical Skills (Must-have):

• Strong proficiency in Python - ability to read, debug, and write automation scripts
• Deep understanding of RESTful APIs, authentication (OAuth, API keys), and troubleshooting tools (Postman, curl)
• Solid understanding of networking fundamentals (TCP/IP, DNS, firewalls, load balancers, VPNs)
• Familiarity with Linux command line for log analysis and system troubleshooting
• Understanding of CI/CD pipelines and deployment processes
• Experience with monitoring and observability tools
• Experience with ServiceNow or similar ITSM platforms

Nice to have:

• Knowledge of Large Language Models, prompting, model inference, and AI platform operations
• Experience with containerization and orchestration platforms
• Familiarity with AWS, Azure, or GCP
• Understanding of ITIL processes (incident, problem, change management)
• Familiarity with authentication, authorization, and security best practices
• Proficiency in Bash or Shell scripting for automation

Soft Skills:

• Excellent Communication:Clear and professional verbal and written communication in English.
• Structured Mindset:Highly organized with strong attention to detail and ability to prioritize effectively.
• Problem-Solving:Strong analytical and troubleshooting skills with a proactive approach to issue resolution.
• Knowledge Sharing:Willingness to share knowledge and contribute to team development.
• Customer Focus:Strong customer service orientation and commitment to user satisfaction.
• Flexibility:Willingness to work across morning, mid, and night shifts as required.
• Attendance and schedule adherence are requirements of this position

#LI-GA1, #LI-HYBRID