I build production-grade cloud infrastructure and agentic AI pipelines on AWS. With a background in biochemistry and biotechnology, I bring scientific precision to the systems I design. Every pipeline I build has deliberate safety guardrails -- minimal permissions, read-only auditors, plan-before-apply gates. Safety is architecture, not discipline. Currently writing a 7-part series documenting the Agentic Infrastructure project: a complete Claude Code pipeline from environment setup to live AWS deployment, SubAgents, MCP integration, and safety hooks. Portfolio: viviancloud.site