AI/LLM Specialist and Digital Operations professional with 3+ years of hands-on experience building agentic prompt systems, rubric-based evaluation frameworks, and LLM QA pipelines that improve reliability, reduce failure modes, and increase stakeholder confidence in AI outputs. I help teams turn ideas into production-ready AI workflows from translating business requirements into prompt architectures, to stress-testing multi-step reasoning, to implementing human-in-the-loop validation for accuracy and safety. On the execution side, I also build automation and integrations (Google Apps Script, APIs, Zapier; AI-assisted dev with independent testing/debugging), and I’m comfortable in healthcare-adjacent workflows (EMR, SOAP documentation, clinical scribing, structured documentation). With a DVM background, I’m especially effective on projects that demand high-precision writing, compliance-minded QA, and domain-aware decisioning but my work translates cleanly to business ops, education, and automation use cases.
Verified
