§ who
Raised in Saipan. Trained as an educator and school counselor. Found my way into AI systems at Amazon — shipping internal tools that replaced manual workflows. Now at EdPlus directing Claude and Codex to build the infrastructure that lets a 5,000+ course operation actually move.
Learning is the pinnacle of human existence.
— the thing I keep coming back toPython + LLM pipelines that audit, generate, and remediate at the per-unit benchmark. Shipped at Amazon. Tested end-to-end at EdPlus.
Stakeholder discovery, scope, regression tests, post-launch metrics. AI is the tool; the workflow is the product.
Per-unit benchmarks, measured rollouts, PartyRock analytics. Numbers tied to the system that produced them — no aggregate handwaving.
§ what I believe
Internal tooling is a force multiplier; the absence of it is expensive theater. AI doesn't replace expertise — it removes the busywork that prevents expertise from showing up. The fastest teams in five years won't be the biggest — they'll be the ones whose builders operate at the intersection of learning science and applied AI.
§ currently
AI Solutions Engineer (Internal title: Instructional Designer)
Sole ID for the MS in Applied Statistics & Data Science. Hand-selected for the Juris Doctor program team. 1 of 3 IDs on the cross-functional AI taskforce.
§ looking for
Teams shipping production AI with measurable business impact — internal tooling, knowledge systems, process automation. Comfortable being the most technical builder in an L&D-adjacent room, or the most learning-science-aware builder in an engineering one.
EdPlus — Python + Claude/Codex pipeline, tested end-to-end
EdPlus — AI authoring plugin, validated end-to-end
EdPlus — same authoring plugin, edit-mode workflow
Project TIES — shipped + ran in production 5 months
Amazon — 44.49% → 69.17% after TIES rollout
SOP-GPT + LearnOps (PartyRock analytics)
AI Solutions Engineer (Internal title: Instructional Designer)
Python + Claude + Codex on Railway; async workers, job queues, batching, retry logic
Per-course audit time: 5 hours → 15 minutes (~95% reduction). Grades against WCAG 2.1 AA + ID rubrics. Tested end-to-end on the 5,000+ course catalog architecture.
Claude-based authoring plugin with embedded WCAG + ID-standards checks, Canvas API integration
Build time per course (with curriculum materials supplied): weeks → 30–60 minutes. Edit time per course: 6 hours → 10 minutes. Validated end-to-end.
Detection, remediation queues, and verification checks joined into one workflow.
Closes the loop between detection and fix — automated audit findings flow into remediation queues with verification checks on the way out. Per-course review-fix-verify cycle reduced ~70% in tested workflow.
Internal Tooling Builder (Internal title: Learning Trainer)
Python + Slack webhooks + Asana + Amazon Quick Suite
Shipped and ran in production for 5 months. Survey participation +56% (44.49% → 69.17%). 80+ hours/quarter/teammate of manual data collection eliminated. ~$50K/yr labor savings (estimated from time × loaded rate). Identified 20% of SOPs as out-of-date on first run.
Articulate 360 with AI-driven branching
5/5 facilitator feedback. Trained 300+ associates with on-time delivery on all L&D submissions.
Logistics Specialist
6,500+ escalation cases at 3% defect rate.
Co-Owner
Operations and financial tracking for a retail automotive service.
School Counselor
Won 20% budget increase via data-driven grant proposal.
+30% performance on complex processes (PartyRock analytics).
+30% workflow efficiency for L&D (PartyRock analytics).
Per-course audit 5h → 15min. Tested end-to-end.
Per-course build weeks → 30–60min. Validated end-to-end.
Recruiter-mode AI chat with JD-fit + comp-band + objection-handling modes. Cloudflare Workers + Anthropic API, prompt-cached.
5/5 facilitator feedback. WCAG-compliant de-escalation simulation.
Boise State University · Coursework
Northern Marianas College · Summa Cum Laude
Northern Marianas College · Magna Cum Laude
Supersedes prior OpenAI AI Foundations and Applied AI Foundations certs
cert. 02
cert. 03