Ziping L.

I am a senior AI systems architect and software engineer with deep experience designing, building, and leading complex AI initiatives under real-world constraints—technical, organizational, and governance-driven. I am also a United States Citizen with a valid US Passport. Over the past several years, I have served as the lead architect and engineer for production-grade AI systems spanning knowledge graphs, retrieval-augmented generation (RAG), agentic workflows, and predictive modeling. My work focuses on transforming ambiguous, high-stakes problem domains into auditable, resilient, and interpretable AI systems that executives, regulators, and technical teams can trust. I have led end-to-end system design—from early research and architecture through deployment, evaluation, and operational hardening—often as the sole technical owner in fast-moving startup and research environments. This includes designing scalable data models, building AI orchestration pipelines, implementing evaluation frameworks, and translating complex system behavior into language that non-technical stakeholders can understand and act upon. A defining feature of my work is crisis-grade composure and governance awareness. I have operated in environments involving executive pressure, reputational risk, regulatory exposure, and internal conflict, where technical decisions could not be separated from organizational consequences. In these settings, I have consistently delivered calm, structured leadership—prioritizing clarity, documentation, risk containment, and long-term system integrity over short-term expediency. Technically, my background spans: • RAG and agentic AI systems, including multi-step reasoning, tool orchestration, structured memory, and guardrails • Knowledge graph architectures (Neo4j) used as computational substrates for reasoning, prediction, counterfactual analysis, and explainability • LLM evaluation and degradation analysis, including prompt drift detection, end-to-end task benchmarks, and comparative model assessment • Production AI infrastructure, including FastAPI services, cloud deployment (AWS/GCP), CI/CD, monitoring, and operational reliability • Graph-based machine learning and predictive pipelines, leveraging structured features and temporal dynamics rather than purely vector-based heuristics Earlier in my career, I worked as a Software Development Engineer at AWS, where I gained strong foundations in production engineering, operational excellence, CI/CD, and cross-team collaboration at scale. That experience continues to shape how I approach reliability, documentation, and stakeholder communication in AI systems today. In addition to hands-on engineering, I regularly operate in architectural, advisory, and mentoring roles—guiding teams on system design, technical decision-making, and responsible deployment. I am particularly effective at bridging gaps between research, engineering, and leadership, ensuring that ambitious AI initiatives remain grounded, defensible, and sustainable. I work best with organizations that value: • Clear thinking over hype • Measurable progress over speculative demos • Governance, safety, and evaluation as first-class concerns • Senior technical leadership that remains calm under pressure Engagements may be part-time or contract-based, including advisory, architecture, or hands-on build roles. I am comfortable operating independently or integrating into existing senior teams, and I prioritize alignment, integrity, and long-term impact in every engagement. If you’re building or stabilizing a high-stakes AI system—and need someone who can both engineer deeply and lead responsibly—I’d be glad to discuss how I can help.