const ken = {
    location: "Manila, Philippines (Remote-ready)",
    role: "AI Full-Stack Engineer @ Romega Solutions",
    building: ["Production RAG systems", "AI agents", "Full-stack platforms"],
    shipped: "42K-LOC internal ops platform — solo, in ~3 months",
    stack: ["Next.js", "TypeScript", "FastAPI", "Supabase", "pgvector", "Claude API"],
    principle: "Ship AI that survives contact with real users — not just demos",
};

I build production AI systems that hold up under real load — RAG pipelines, autonomous agents, and full-stack applications taken from idea to live deployment, often solo.

Most recently I shipped an all-in-one internal operations platform on my own in about three months: 46 pages, 56 API routes, a 31-table Postgres schema, ~42K lines of TypeScript — native ticketing, a recruiting ATS, an LMS, and LLM-powered reporting, plus a zero-downtime migration off a third-party PM SaaS.

My focus is the engineering that makes AI dependable, not just impressive in a demo: retrieval that surfaces the right context, agents that fail gracefully, and architectures built for reliability, cost, and scale from the first commit. AI outputs land in human review queues — never auto-published. I care less about what looks good on stage and more about what's still running at 2 AM.

Recent Highlights:

• 🏆 Champion — C(Old) (St)art Hackathon 2025 (Old St. Labs)
• 🥈 1st Runner-Up — InfoTech Olympics 2025 (PaceBeats)
• 🎯 National Top 10 — DOST-TAPI ClustRICE 2025 (HerbaLens, 53 entries)
• 🎤 Speaker — Qwen Meetup Manila #2 (Alibaba Cloud PH)

AI Full-Stack Engineer @ Romega Solutions · Remote Jul 2025 – Present

• Shipped an all-in-one internal operations platform solo — 46 pages, 56 API routes, a 31-table Postgres schema, ~42K lines of TypeScript in ~3 months (PM/ticketing, attendance, recruiting ATS, LMS, AI reporting).
• Led a zero-downtime migration off a third-party PM SaaS: rebuilt ticketing natively (kanban, sprints, comments, activity feeds), migrated SQLite → Supabase Postgres with Drizzle ORM, replaced custom JWT auth with Supabase Auth + Google OAuth.
• Integrated LLM features (executive briefings, AI status-report drafting) and n8n automations (resume parsing, applicant comms, multi-step onboarding) into business workflows — outputs route to human review queues, never auto-publish.
• Shipped production RAG chatbots with vector embeddings (ChromaDB · sentence-transformers · Gemini) for customer interactions and workflow automation.

Lead Software Engineer @ PaceBeats · Remote Aug 2025 – Mar 2026

• Architected a biometric music platform (1st Runner-Up, InfoTech Olympics 2025): WearOS app (Kotlin, Health Services API), Android app, React/TypeScript dashboard, Supabase backend.
• Built a hybrid recommendation engine combining rule-based pace-to-BPM mapping with content-based ML scoring — real-time playlist adaptation.
• Engineered the WearOS companion: GPS tracking, heart-rate monitoring, Data Layer API sync, Spotify SDK, 8+ hour battery optimization.

Software Engineer (Contract) @ CodeVF · Remote Feb 2026 – Apr 2026

• Built a real-time collaboration platform with WebSocket architecture for live debugging sessions between customers and engineers — bidirectional code review and remote assistance.

AI Workflow Automation Engineer @ University of Makati · Remote Jan 2026 – Apr 2026

• Built n8n automation workflows to streamline administrative processes and data pipelines.

Earlier: VCM hardware deployment for COMELEC national elections (2025); enterprise SaaS technical support at Concentrix (2024).