I am a mechanical designer with 5+ years of experience supporting high-volume electrical-equipment manufacturing. My work centers on production-ready mechanical configurations, BOM and revision accuracy, engineering releases, quality checks, manufacturing support, and workflow improvement.
I am building toward applied-AI roles that connect engineering domain knowledge with practical automation. My focus is not replacing engineering judgment. It is designing controlled AI-assisted workflows that help teams extract requirements, detect exceptions, compare revisions, summarize technical information, and prioritize review while keeping qualified people responsible for final decisions.
AI Solutions and Automation for Manufacturing & Engineering
Relevant role families include:
- AI Solutions Analyst
- AI Automation Specialist
- Manufacturing AI Specialist
- Engineering AI Workflow Specialist
- Digital Manufacturing AI Specialist
- AI Business Analyst for Engineering Operations
- Mechanical design for high-volume manufacturing
- Production-ready engineering configurations and releases
- BOM management and revision control
- Manufacturing issue resolution
- Design-quality auditing
- Cross-functional work with engineering, manufacturing, quality, and operations
- Creo, SAP, ETQ, TDMS, Excel, and Power Query experience
- AI-assisted engineering workflow design
- Retrieval-augmented generation concepts
- Technical-document extraction and summarization
- Human-in-the-loop validation
- Responsible-AI controls and traceability
- Python, SQL, Google Colab, Google Sheets, and GitHub
- Data validation, KPI design, workflow automation, and analytical reporting
Status: Active flagship upgrade
An independent portfolio project using synthetic manufacturing data to evaluate BOM errors, revision activity, rework impact, resolution performance, and engineering-release integrity.
Current strengths:
- Formula-driven KPI dashboard
- BOM error and revision-change tracking
- Rework-cost and resolution-time analysis
- Synthetic manufacturing dataset
- Operational recommendations
Current development focus:
- Formal data dictionary and validation rules
- Google Sheets compatibility
- Reproducible Google Colab validation pipeline
- Controlled AI-assisted exception summaries
- Human approval, traceability, testing, and responsible-AI documentation
Status: Business case and pilot concept
A manufacturing-focused use case exploring how generative AI could support specification research, routine documentation, engineering-change summaries, and design-workflow efficiency without transferring final engineering authority to AI.
Status: Existing technical project scheduled for validation
A Python-based document-processing project that will be reviewed for reproducibility, testing, event traceability, exception handling, and practical applied-AI value.
Status: Existing RAG project scheduled for validation
A document-question-answering project focused on making educational information easier to retrieve and understand. Planned improvements include grounded answers, source citations, retrieval evaluation, privacy controls, and clear human-review boundaries.
AI may assist with drafting, classification, summarization, code scaffolding, test-case ideas, and debugging explanations.
I remain responsible for:
- Defining the business and engineering rules
- Inspecting source data
- Selecting and validating metrics
- Reviewing and testing generated code
- Investigating exceptions and anomalies
- Documenting assumptions and limitations
- Protecting confidential information
- Approving every final deliverable and decision
AI does not approve BOMs, engineering changes, component selections, design releases, root causes, or production decisions.
My projects are being strengthened one at a time through a professional delivery lifecycle:
- Business and stakeholder requirements
- Current-state audit
- Data provenance and quality validation
- KPI definition and manual reconciliation
- Reproducible processing
- Applied-AI workflow design
- Testing, security, and responsible-AI review
- Stakeholder-ready documentation and demonstration
All portfolio projects use synthetic, anonymized, user-owned, or publicly available data. They do not contain confidential employer, customer, product, drawing, pricing, or proprietary process information.
- Associate of Applied Science, Mechanical Design Technology
- Information technology studies
- Training in data analytics, business intelligence, Python, Excel, AWS cloud engineering, and IT automation
Building practical, human-reviewed AI workflows for manufacturing and engineering.