Alexander
Vervloet.
For eight years I shipped production React and React Native to millions of users. Now I build AI systems from scratch — RAG, agents, evals, guardrails — to understand them at the primitive level, not the framework level. The throughline is the same: I translate between how a system actually works and what a team is trying to build.
drop /portrait.duotone.jpg in public/
What I bring beyond the code.
At VeVe I was never just the person who built things. I was the person who asked why we were building them, whether we were building the right thing, and how to explain the answer to someone who had never written a line of code.
That combination of technical fluency and communication instinct is the part of the job I enjoyed most — and it shows up in everything from the quality of my pull requests to the questions I ask in a planning meeting.
- →Asking why, not just how.
- →Explaining complex systems in plain language.
- →Feedback in planning that changes the plan.
- →Knowing when not to ship.
- →Teaching — three years, in two languages.
Eight years. One long streak.
- 01Building AI-engineering systems from scratch (no frameworks) to understand the primitives, not just the libraries — RAG pipelines, tool-using agents, eval harnesses, and prompt-injection defenses, each a runnable project with measured results.
- 02Shipped three distinct flagship projects that span building, running, and orchestrating LLM systems: askrepo, a codebase-Q&A app answering with (path:line) citations across eight eval-gated stages; a self-hosted local-LLM news pipeline with its own eval suite and guardrails; and a harness that stress-tests the spec-driven-development workflow with gated phases and deterministic traceability checks.
- 03Publishing the work as an open, teachable series spanning RAG, agents, evals, guardrails, MCP, multimodal, fine-tuning, and local models.
- 01Built the complete new-user onboarding flow for the mobile app launch — a 10-step guided experience that drove tens of thousands of signups in the first weeks and millions in early revenue.
- 02Owned the web payment flow for in-app currency purchases end-to-end. Millions of dollars processed. Zero critical payment bugs shipped.
- 03Built the web storefront, auction bidding system, and direct-purchase flows from scratch — the primary revenue surface for hundreds of thousands of transactions.
- 04Served as the technical translator between engineering and product. Brought into executive meetings specifically to explain complex system behavior in plain terms.
- 05Most active contributor in every planning session across six years. Highest rate of feedback adopted. Regularly the only person asking: should we actually build this?
- 01Led frontend in a small agile team building a React platform matching brands with influencers — shipping weekly through constantly changing specs.
- 02Drove a 500% improvement in measured customer satisfaction through targeted testing, tooling improvements, and systematic refactoring.
- 01Built and maintained frontend features using React, React Native, and D3.js in a fully remote agile team, coordinating across time zones from day one.
The stack.
- LLM apps · RAG · agents
- Evals · LLM-as-judge
- Prompt engineering · guardrails
- Python · FastAPI
- OpenAI · Anthropic · local models
- Vector search · MCP
- JavaScript / TypeScript
- React · React Native
- Node.js · NestJS
- REST · GraphQL
- Web3 / Blockchain
- Payment systems
- Unit / E2E testing
- UI / UX feedback
- Technical communication
- Cross-team collaboration
- Product-minded thinking
- Explaining complexity simply
Things I build outside the job.
Building in the open.
Three years in a classroom.
Before moving into full-time engineering I taught English and core subjects at schools in Taiwan — including one of the country's top-ranked high schools. Math, science, social studies. Often in Mandarin. Gamification and question-driven methods.
I also tutored privately — students from age 6 to working professionals, on everything from English to beginner Python and Raspberry Pi hardware.
The discipline of making complex things genuinely simple for people with no prior context has turned out to be the single most useful thing I do.
- English
- Native
- 中文 Mandarin
- Intermediate · self-taught, 12 years in TW
- B.S.
- Communication — Speech, Rhetoric, Leadership
- School
- Oregon State University, 2014
- Major GPA
- 3.65
Start a conversation.
I'm open to remote roles in AI/ML and full-stack engineering with teams who value communication as much as code. I'm also open to PM or TPM positions, as I have a wealth of experience focusing on product and working with them directly. UTC+8, flexible overlap with US and EU.
- alex.vervloet [at] gmail [dot] com
- alexander-vervloet
- GitHub
- @alexvervloet