I work at the intersection of multi-agent LLM systems andsystematic trading research. The through-line is a single engineering principle: don't ship what hasn't passed a measurable quality gate.Eleven agents in an orchestrator-worker topology. A 31-gate statistical evaluation harness. Pre-registered research windows. Public-data reproducibility. Headline metrics you can verify.
I was previously the AI Systems Engineer / Quantitative Researcher on the19V Capital desk under PM Evan Ferioli (closed past contract, 03/2026 – 06/2026), where the same eval harness served both LLM outputs and systematic trading strategies. Before that I shipped a 7-agent venture-incubation pipeline under Macion Ventures, an 8-agent content-production pipeline for editorial automation, and a portfolio of runnable AI projects (RAG scorecard, ReAct tool-calling agent, MCP eval server, LLM-as-judge harness, reflection agent, AI-slop evaluation gate).
On the quant side I design and backtest systematic strategies on crypto and equities — nine reproducible public-data projects spanning multiple-testing (Deflated Sharpe), cross-sectional and time-series alpha, volatility carry, cointegration, funding-carry, regime overlays, transaction-cost realism, and look-ahead-bias audits. Every project ships with the standard senior-research discipline: locked OOS windows, block-bootstrap CIs, and the methodology stated up-front, not bolted on at the end.
I'm based in Digos City, Davao del Sur, Philippines (UTC+8), available 30 hrs/wk remote. I hold 102 professional certifications across AI, finance, math/statistics, and event flagships, built up in 11 months. I write about what I'm learning and ship the things I'm building.
