PLM Engineer

Position: PLM AI Engineer

Location: Sunnyvale, CA (onsite)

12 months

Job Description:

Key Responsibilities

• Design and build an AI-powered support bot (web/chat-based) for Hypercare query resolution
• Develop agentic workflows to retrieve and synthesise answers from:
• Past incident tickets
• Knowledge bases and documentation
• PLM (Teamcenter) systems
• Implement RAG / multi-source retrieval pipelines for contextual and accurate responses
• Build APIs and backend services using Python (FastAPI) and Apple-approved AI frameworks
• Ensure compliance with Apple security, governance, and AI platform constraints
• Collaborate with Hypercare, PLM, and support teams to continuously improve response accuracy

Core Requirements

• Strong experience in Python backend development (FastAPI preferred)
• Hands-on in building LLM-based systems (RAG, agentic workflows, knowledge assistants)
• Experience in data integration from multiple enterprise systems (tickets, logs, APIs)
• Good understanding of support workflows, incident triage, and knowledge management systems
• Strong API design, microservices, and distributed system fundamentals

Preferred / Good to Have

• Experience in PLM domain (Agile / Teamcenter)
• Exposure to Hypercare / production support environments
• Experience working with enterprise AI platforms and governed environments

Success Criteria

• Reduce mean time to resolution (MTTR) during Hypercare
• Enable self-service query resolution for support engineers
• Deliver a scalable AI support framework for future releases