I am an AI Engineer building agentic and LLM systems that must work reliably and safely in production, especially in regulated, high-stakes environments. I design rule-based and LLM-based checks routed through deterministic decision logic, human-in-the-loop escalation, and complete audit trails. My core project, SINTEZA, is a clinical decision-support safety pipeline with evaluation harnesses, guardrails, and traceability aligned to EU AI Act logging and human oversight expectations. I’m comfortable across the full Python pipeline—from data to deployed services—and translate technical trade-offs for clinical, product, and non-technical stakeholders.…I am an AI Engineer building agentic and LLM systems that must work reliably and safely in production, especially in regulated, high-stakes environments. I design rule-based and LLM-based checks routed through deterministic decision logic, human-in-the-loop escalation, and complete audit trails. My core project, SINTEZA, is a clinical decision-support safety pipeline with evaluation harnesses, guardrails, and traceability aligned to EU AI Act logging and human oversight expectations. I’m comfortable across the full Python pipeline—from data to deployed services—and translate technical trade-offs for clinical, product, and non-technical stakeholders.WWWW…