01Currently building · AI accessibility platform
Paperlyft
Turns complex documents into WCAG 2.1 AA and PDF/UA-ready output, pairing an AI processing pipeline with evaluation, human review, and AWS infrastructure.
AI engineerArizona / Earth
Visionbeyondreality.
I build what matters, understand why it works, and never stop making it better.
PORTFOLIO / 2026SHIP · MEASURE · IMPROVE33.4484° N · 112.0740° W
Selected transmissions · 2024-26
Systems that left the lab.
Production work, active bets, and experiments that kept moving after the demo.
02Public developer tooling · LEI
Critical Code Reviewer
Research-backed context and review tooling for Claude Code, with branch-local continuity, privacy-aware evidence, reusable review contracts, and an advisory GitHub Action path.
03Nonprofit platform · live production
NMTSA.org
A nonprofit platform with CMS-driven pages, admin operations, dynamic forms, donations, and payments, built by a team to help families, professionals, and donors find and request services.
04Hobby project · AI workspace
vctrx.ai
A project workspace where Kanban, documents, journals, and Studio intake are connected by a multi-agent LangGraph orchestration layer with durable state and role-aware workflows.
05Personal project · AI career tooling
Final Destination
A personal job-search cockpit for tailoring resumes and cover letters, answering application questions, tracking H-1B opportunities, and processing job batches from a browser extension.
Method / operating principles
Structure turns intelligence into a system.
I design AI around measurable behavior, observable failure modes, and repeatable delivery - not impressive demos that drift in production.
That method runs through Paperlyft and my code-review work at ASU. Different problems; the same demand for evidence over claims.
Structure beats intelligence.
A well-scoped agent with the right context usually beats a smarter model with no boundaries.
Accountability is architecture.
If a decision cannot be traced to an agent, context, and rule, the system is not production-ready.
Consistency earns trust.
One reliable capability is more valuable than ten impressive behaviors that drift between runs.
Trajectory
Founder & engineer · Vctrx
Designing the orchestration, memory, authority, and infrastructure layers for reliable agent teams.
Working instruments
- LangGraph
- Agent skills
- Claude Code
- OpenCode
- Codex
- CrewAI
- MCP
- RAG
- Vector databases
- LLM evaluation
- Prompt architecture
AWS credentials
AWS Certified Cloud Practitioner · AWS Academy Graduate - Cloud Security Foundations Training Badge
Interests / future work
Curious about what comes next.
My work is rooted in education, while my curiosity keeps pulling me toward finance and the edges of computation.
01Building now · ASU LEI
Education
Currently working at the Learning Engineering Institute to help change the world of education - building technology that makes learning more accessible, more useful, and more human.
Learning as a force multiplier
02Learning toward
Finance
I’m drawn to finance for the way it combines data, uncertainty, incentives, and long-horizon decisions. I want to keep learning the systems behind the numbers and eventually build within them.
Markets · decisions · systems
03Curiosity frontier
Quantum computing
Quantum computing interests me because it asks us to rethink what computation can be. I’m learning about the field simply because the ideas are fascinating - and to see where they may lead.
A different way to compute
Common thread
Different domains. The same question: how can thoughtful systems expand what people are able to do?
Field notes