user | profile |

$ whoami

Zachary Montague

AI Systems Engineer | Cloud, Reliability & Security

I put AI into the work you already do

Zac Montague builds, secures, and operates production AI and cloud systems. He partners directly with investment, compliance, and business teams to turn an operational problem into a working system, then trains people to use it.

  • 12+ years across cloud architecture, SRE, and enterprise security.
  • Multi-agent AI systems built for production.
  • Implementation and technical enablement, together.
cat experience.log ./contact.sh ./research --ai

Working with a small number of companies

Terminal below. Try help, neofetch, or cd experience. Press ` to focus.

identity.img verified

Zachary Montague, professional photo

About Zac

Senior infrastructure and AI systems engineer with 12+ years of experience across cloud architecture, site reliability engineering, and enterprise security. I partner with investment, compliance, and executive teams to scope, build, secure, and operate production systems, combining Kubernetes, AWS, and zero-trust security with multi-agent orchestration and LLM pipelines.

I founded Nomad Cybersecurity Group, worked as a Site Reliability Engineer at Gen, and built AWS and Azure environments at Saint Louis University. My career began in technical support and systems administration in 2006.

From 2021 to 2023, I also provided pro bono cloud consulting to local real estate, retail, grocery, and accounting businesses, guiding cost-effective AWS EC2 and Lightsail migrations.

Experience

A career in systems since 2006, with 12+ years across cloud architecture, reliability, and security. Current work focuses on production AI systems.

Principal Security Consultant & Founder

Nomad Cybersecurity Group

Nov 2023 to Jun 2026 Remote
  • Managed a security consultancy focused on cloud hardening, immutable infrastructure design, and adversarial auditing for enterprise clients.
  • Delivered cloud and infrastructure security consulting for Pursuit Ltd, including architecture reviews, infrastructure hardening, remediation planning, and zero-trust access controls.
  • Submitted valid, rewarded DeFi security findings through public audit contests on Code4rena, Sherlock, and CodeHawks, and vulnerability hunting on Immunefi.

Site Reliability Engineer

Gen

May 2022 to Nov 2023 Remote
  • Designed custom SLIs and SLOs and Python observability pipelines in Datadog for 10-50 core production services.
  • Automated incident-response workflows with Python and PagerDuty.
  • Deployed access-controlled ArgoCD GitOps workflows with hardened Kubernetes configurations and audit trails, cutting deployment error rates by 40%.

Cloud Engineer

Saint Louis University School of Medicine

Feb 2020 to May 2022 St. Louis, MO
  • Designed AWS environments for researchers handling sensitive medical data with KMS/TLS controls.
  • Automated VPC and security-group provisioning with Terraform and Ansible, producing auditable infrastructure changes.
  • Provisioned HPC resources and managed compute and storage costs for research workloads.
  • Developed and tested disaster-recovery plans against target Recovery Time Objectives (RTOs).

Cloud Engineer

Saint Louis University

Jul 2019 to Feb 2020 Remote
  • Architected AWS and Azure infrastructure for university academic and administrative applications.
  • Built Jenkins and GitLab CI pipelines to standardize delivery across engineering teams.
  • Implemented autoscaling to support high-traffic academic registration periods.

Senior System Administrator

RnS Distribution

2017 to 2019
  • Led enterprise cloud migration initiatives and core Linux infrastructure modernization.

System Administrator

Stoopid Chikin

2015 to 2017
  • Managed systems operations, network stability, and infrastructure reliability.

Technical Support & Junior Administrator Roles

Early career

2006 to 2015
  • Built foundational expertise in IT infrastructure, troubleshooting, and systems administration.

Expertise

AI in the work you already do

Records, follow-up, intake, the messy stuff in email and spreadsheets. Built into the workflow, not parked in a chatbot nobody opens.

Build or teach

I leave you a running system, then train your people to operate it. Most engagements combine implementation with AI and agent enablement.

Production operations

Kubernetes, observability, incident automation, and infrastructure that survives audits and outages. Same habits, now applied to AI.

Human review when it matters

Gates before anything customer-facing. Escalation by severity. Automation that knows when to stop.

Agentic & AI

  • LangChain
  • Model Context Protocol (MCP)
  • Multi-agent orchestration
  • Retrieval-augmented generation (RAG)
  • Agent evaluation
  • Tool and API integration
  • AI governance

Infrastructure

  • AWS
  • Azure
  • Kubernetes
  • Terraform
  • Ansible
  • Docker
  • Linux
  • ArgoCD / GitOps
  • Jenkins
  • GitLab CI
  • Python
  • FastAPI
  • REST APIs
  • Bash

Security & Compliance

  • OpenTelemetry
  • Datadog
  • PagerDuty
  • SLI/SLO design
  • Microsoft Entra ID
  • Identity and access management
  • Zero trust
  • Sandboxed execution
  • Vulnerability scanning
  • Smart contract auditing
  • Solidity (audit)

Enablement

  • Technical training
  • Requirements
  • Stakeholder management
  • Solution architecture

Featured Work

In progress

SOUL ICM Second Brain

A source-backed operating brain, not a chatbot

Problem

Important context is scattered across documents, decisions, workflows, and people. An AI system that cannot show its sources, respect boundaries, or recognize uncertainty turns a knowledge problem into a trust problem.

Approach

The Interpretable Context Methodology (ICM) second brain routes work through a file-native corporate vault, source-backed knowledge, deterministic validation, and founder-controlled approvals. Client context stays in isolated vaults, while agents prepare and check work without promoting their own output to truth.

Architecture

Deterministic routing from incoming evidence to approved, reusable context. Click a step to expand.

Intake
Capture and classify

An incoming request or source is classified, bounded, and routed to the one workspace authorized to handle it.

Source register
Record provenance

Sources carry stable identifiers, classification, ownership, review dates, and enough provenance to support later checking.

Workspace route
Use deterministic context

Company direction, delivery, governance, technology, and other workspaces keep retrieval narrow and explainable.

Verified knowledge
Retrieve with limits

Lookup returns source-backed, approved context from the selected vault and explicitly abstains when the evidence is not sufficient.

SOUL layer
Value context and learning

The Company Soul and isolated Client Souls organize value, decisions, signals, and proposed learning without silently changing authority.

Founder review
Approve promotion

A human approves durable truth, publication, transfer, or generalization. The system records what changed and why.

Private architecture walkthrough available on request.

Read the full case study →

Corporate vault

A file-native operating brain with routed workspaces, source registers, and explicit information-classification rules.

ICM validators

Deterministic Python checks for structure, metadata, provenance, scope, review state, and client-boundary safety.

Verified knowledge lookup

Searches one explicitly selected vault for source-backed knowledge and abstains when context is missing, stale, conflicting, or unauthorized.

Client-vault boundary

Opaque-ID client repositories keep client context separate from the corporate brain and from every other client.

Governance safeguards

  • Founder approval is required for durable knowledge, publication, and generalization
  • Client content stays in its client vault; only approved, redacted learning can move upward
  • Agents and contributors prepare and validate work but cannot approve or own truth
  • Missing, stale, conflicting, or unauthorized context produces abstention or escalation

Education & Credentials

  • Build Reliable AI Workflows Completed
    LaunchCode / HireHuman - Agentic AI Program

    Agentic AI Program, 2026.

FAQ

Straight answers about the work.

Do you still do cybersecurity?

No. That chapter is closed. Nomad Cybersecurity Group is in the past. New work is AI operations and teaching, not security auditing.

How do you work with a company?

Two ways. I build the thing and leave it running. Or I sit with your people and teach them to run it. Most clients want some of both. You do not get a deck.

Are you taking work?

Yes, a small number of companies at a time. LinkedIn.

Research Zac with AI

Click a platform to read this site, LinkedIn, and public GitHub work, then get a plain summary of who Zac is and what he does.

ChatGPT Claude Gemini Grok Copilot

If a platform does not auto fill, paste the copied prompt after it opens. Machine readable context also lives at /llms.txt and /llms-full.txt.

Preview research prompt 
Open to load prompt preview.

Let's put AI into the work you already do

This page is me. Connect with me on LinkedIn for professional inquiries.

LinkedIn

Resume available on request via LinkedIn. GitHub is provided for public code and project work.