AI QA Engineer · LLM Evaluation Specialist · Implementation Consultant
I build quality assurance systems for Generative AI — from evaluation frameworks for enterprise deployment to HIPAA-compliant AI agents.
- LLM Evaluation & Validation — behavioral testing, output quality scoring, safety, and bias assessment for large language models
- AI Implementation Consulting — requirements to deployment pipelines for enterprise AI systems (IBM watsonx, LangChain, RAG architectures)
- AI Safety Architecture — 4-layer safety design: input validation → RAG constraints → output filters → MLflow audit logging
- GRADE Framework — 11 failure patterns for store-level AI agents, 56 benchmark files, systematic evaluation methodology for AI agent reliability
| Project | Description | Stack |
|---|---|---|
| Healthcare AI Agent | HIPAA-compliant agent · 4-layer safety · zero critical findings in simulated audit | IBM watsonx · RAG · MLflow |
| Retail AI Intelligence | GRADE Framework · 11 failure patterns · evaluation methodology & benchmark suite | LangChain · Python · RAG |
| Weather App QA | 6 automated tests · input validation, encoding, DOM rendering | Mocha · Chai · JavaScript |
Authored methodology for evaluating Store-Level AI agents in production.
11 failure patterns · 56 benchmark files · 15-20 scenarios per pattern
| Severity | Patterns |
|---|---|
| 🔴 Critical | P1 Granularity Boundary · P3 Asymmetric Error Tolerance · P10 Sycophancy |
| 🟡 High | P2 Prompt Quality Variance · P6 State Drift · P9 Context Contamination |
| 🟢 Moderate | P4 Role Inversion · P5 Adaptive Failure · P7 Reasoning Degradation · P8 Instruction Sensitivity |
| 🔵 Extended | P11 Intent-to-Prompt Gap |
AI/LLM Evaluation: IBM watsonx · LangChain · MLflow · RAG
Development: Python · JavaScript · Mocha/Chai · Playwright
Cloud & Infra: AWS (Terraform) · GitHub Actions · CI/CD
- IBM AI Certificate 2025 (watsonx · Enterprise Design Thinking · Granite)
- Google Foundations of Data Science 2025 (Coursera)
- Generation USA AI Training 2025
- Full Stack Web Dev — Wilmington University, Dean's List
- 25+ total credentials
📌 Boise, Idaho, USA 🎤 Idaho CTE AI Panel Speaker — July 2026 🔗 LinkedIn
Open to AI QA Engineer, LLM Evaluation Specialist, AI Implementation Consultant, AI Product QA, AI Operations, and Technical Product Owner (AI) roles — remote-first, Boise, Idaho.