// ai infrastructure engineer
Infrastructure engineer specializing in AI systems — agentic AI, agentic orchestrators, and the infrastructure that runs them.
View My WorkThe AI systems I built compressed enterprise ServiceNow delivery — six-month project timelines to a few weeks, day-to-day and business configuration from weeks to days — and let a small team punch well above its weight.
Led the ServiceNow-side rollout of Webex Contact Center on a CSM-first model — case handling, live notes, and Advanced Work Assignment routing — validated against a reusable Webex API emulator.
Turned a single ServiceNow catalog request into tracked engineering work — an intake pattern that splits it into child items and opens a linked Azure DevOps epic automatically.
Built the reporting layer leadership actually reads — platform analytics for executives and managers, branch and ITSM performance dashboards, and automated monthly output reporting in ServiceNow.
Connected LogicMonitor and Tenable into ServiceNow — monitoring alerts to outage/incident records and normalized vulnerability naming — so ops and security worked from one source of truth.
Reverse-mapped a Saviynt scoped application inside ServiceNow — workflows, catalog items, REST footprint, and schedulers — into a clean operational guide the team could run against.
A bring-your-own-LLM workspace that turns any AI assistant into a capable ServiceNow senior admin — safe read-only instance recon, 16 platform-specific skills, and enterprise-grade hardening (OAuth, audit logging, CIS-hardened container).
A reference implementation for AI-agent audit trails: tamper-evident, automatic, examiner-ready records that prove what an autonomous agent actually did. Maps to the EU AI Act, ISO 42001, SOC 2, and NIST AI RMF. Open source coming soon.
Turns live threat intelligence into a SOC-grade briefing as a single self-contained HTML file — no install, no dependencies, no standing API key — and hardened against its own attack surface via a NIST 800-30 self-audit.
A config-driven, multi-tenant engine I built — now in pilot — that turns raw scanner findings into prioritized, plain-language, owner-routed remediation work. Strictly defensive, with an audit trail behind every decision.
A structured AI workspace that loads real defensive-security doctrine, methodology, and skills into an AI assistant so it operates like a senior Blue Team practitioner — consistent, auditable, and framework-grounded.
Earned Securiti's AI Security & Governance certification — core generative-AI concepts, global AI laws, compliance obligations, AI risk management, and AI governance frameworks. The compliance counterpart to the AI systems I build.
Full-featured agentic AI system built on Claude Code. Multi-phase execution engine, 49 skills, lifecycle hooks, persistent memory, and a voice interface — running on Bazzite Linux.
Fully automated deployment pipeline. Python file watcher + GitHub Actions + SSH deploy to Namecheap. Changes go live within seconds of a local edit.
Two Python CLI tools for converting PDFs and Word documents to LLM-ready Markdown. pdf2md handles books and batch jobs. paper2md handles multi-column research papers.
Built a catalog item that queries a banking API in real time — auto-populating customer name and account type as the user types, with automatic Help Desk routing on submission.
Designed and deployed a Claude-powered self-service chat bot inside ServiceNow — giving employees instant answers about their tickets, requests, and catalog items without opening a single form.
Took the AI chat widget from a working prototype to an enterprise-ready app — adding four role-based tiers, L1 troubleshooting flows, write actions, audit logging, rate limiting, and CIS-compliant credential storage.
The next leap in AI-augmented work isn't a better model. It's a better system around the model. Here's the architecture I built — and why Claude Haiku inside it outperforms raw Claude Opus on the same tasks.
Built and tuned a self-hosted LLM inference server on a single consumer GPU — nearly tripling its throughput with smarter model placement — then made it privately shareable with a team over an encrypted mesh network with key-based auth.
Built and deployed a doctrine-driven compliance assistant for a paying regulated-lending customer — cited retrieval over the federal regulations they answer to, role-locked operators, and a private in-tenant model so sensitive data never leaves their control. Solo, and live in production in a few weeks.
Built an autonomous, AI-augmented offensive-security operator — codenamed Harkonnen — that works a target from recon to written report. I run it on sanctioned labs, CTFs, hackathons, and live bug-bounty programs, with a human in the loop on every consequential move.
Completed DeepLearning.AI's Agentic AI program. The labs covered tool-calling loops, multi-agent decomposition, reflection, planning, and evals — patterns I'd already been building into production systems. Here's the honest take on what a cert adds when you've been doing the work first.
Harkonnen, my self-learning agentic orchestrator for offensive security, placed top-25 of ~300 fully autonomous AI agents in Hack The Box's MCP pilot — clearing 36 of 37 challenges across every category on the board.
NVIDIA's AI Infrastructure and Operations Fundamentals — my deliberate first step from traditional infrastructure into the systems and operations that run AI in production.
AI infrastructure engineer and systems builder with 6+ years across banking, healthcare, and tech. Over the last couple of years my focus shifted from traditional infrastructure and automation into AI systems — building the agentic orchestrators, self-hosted model backends, and governance tooling that AI actually runs on.
I'm especially interested in how AI can improve real operational work — not just demos or hype, but tools that actually save time, reduce friction, and help people solve problems faster. Most of the projects in this portfolio come from experimenting, building, and figuring things out hands-on.
Right now I'm focused on agentic AI, infrastructure for AI tools, automation pipelines, and integrating AI into enterprise platforms like ServiceNow — with a growing emphasis on the security and governance side, since the fastest-moving risk in AI is regulatory, not technical. I've backed that direction with certifications from NVIDIA (AI Infrastructure and Operations), DeepLearning.AI (Agentic AI), and Securiti (AI Security & Governance).
This site is a running collection of projects, experiments, and lessons learned as I continue exploring where AI fits into real-world infrastructure and operations.
Want to get in touch? Find me here.