Platform Support AI Trainer

Job Description: Platform Support AI Trainer
Location: Hybrid (Columbia, SC or Remote) Only from CST/EST
Duration: Contract
Over 12-13years
Key skills: AI Developer with – Python, azure apim, langraph, langchain, genAI, added adv - azure devops
Summary:
We are is seeking a Platform Support AI Trainer to lead the integration of AI into our Platform Engineering operations. This role will be responsible for curating, structuring, and maintaining the knowledge base that powers our AI assistant (Copilot), enabling it to provide accurate, context-aware support for platforms such as OutSystems, AutoRABIT, and Azure API Management (APIM).
Key Responsibilities:

• Curate and ingest internal and vendor documentation, tickets, change requests, and platform-specific knowledge into the AI system.
• Collaborate with platform SMEs to validate and refine AI-generated outputs.
• Design and maintain workflows for continuous learning and feedback loops between the AI and engineering teams.
• Monitor AI performance and identify areas for improvement in accuracy, relevance, and usability.
• Develop prompt templates and usage guidelines for engineers to interact effectively with Copilot.
• Ensure compliance with data governance, security, and privacy standards.

Qualifications:

• 3+ years in platform engineering, DevOps, or technical documentation.
• Familiarity with OutSystems, AutoRABIT, Azure APIM, or similar platforms.
• Experience with AI/ML tools, prompt engineering, or knowledge management systems is a plus.
• Strong analytical, communication, and organizational skills.

Business Case for AI-Supported Platform Engineering
Objective:
To enhance platform reliability, reduce MTTR (Mean Time to Resolution), and improve engineering productivity through AI-assisted knowledge management and operational support.
Key Benefits:
Operational Efficiency

• Instant access to historical tickets, change logs, and documentation.
• Automated summarization and contextual answers reduce time spent searching for information.

Break/Fix Acceleration

• AI can suggest known fixes, identify patterns in recurring issues, and recommend escalation paths.
• Reduces dependency on tribal knowledge.

Onboarding & Training

• New hires can ramp up faster with AI-guided walkthroughs and contextual answers.
• Reduces training overhead for senior engineers.

Documentation Enhancement

• AI can flag outdated or missing documentation based on user queries and gaps in responses.
• Supports continuous documentation improvement.

Scalability

• AI scales with the team, providing consistent support regardless of team size or turnover.

Strategic Insights

• Analyze trends in platform issues, usage patterns, and support gaps to inform roadmap decisions.

3. Outline: AI-Supported Platform Engineering Team Process
Phase 1: Foundation

• Hire AI Trainer
• Audit existing documentation and ticketing systems
• Define taxonomy and tagging standards for ingestion
• Establish data governance and access controls

Phase 2: AI Enablement

• Ingest and structure documentation (internal, vendor, tickets, SOPs)
• Train Copilot on platform-specific terminology and workflows
• Develop prompt templates for common tasks (e.g., "How do I deploy to OutSystems staging?”)

Phase 3: Integration

• Embed Copilot into daily workflows (e.g., ticket triage, change request reviews)
• Pilot with a small group of engineers
• Collect feedback and iterate on AI responses

Phase 4: Optimization

• Implement feedback loops (e.g., thumbs up/down, correction suggestions)
• Monitor usage metrics and accuracy
• Expand to additional platforms or tools

Phase 5: Continuous Improvement

• Monthly knowledge base updates
• Quarterly AI performance reviews
• Annual retraining or fine-tuning based on platform evolution