Senior DevOps & AI-Assisted Engineering

I build systems and operating workflows where AI work is bounded, reviewed, and verified.

I combine long-term DevOps and infrastructure experience with ChatGPT, Codex CLI, Git, RFC-driven delivery, observability, and session evidence so AI-assisted engineering stays practical, auditable, and under human control.

About

My background is in Linux systems, infrastructure automation, networking, virtualization, containers, CI/CD and platform operations. I now apply AI-assisted engineering as a reviewed repository workflow: define architecture and constraints, break work into RFC-sized tasks, use Codex CLI for bounded implementation, validate the result, preserve sanitized session evidence, and take responsibility for integration, security and operations.

What I do

Build new projects

From initial idea and architecture to a working, deployable system with infrastructure, observability and documentation.

Take over existing systems

Understand unfamiliar code and infrastructure, identify operational risks, stabilize the environment and establish a maintainable workflow.

AI-assisted engineering

Use ChatGPT and Codex as engineering tools for architecture, RFC preparation, repository work, validation and iterative delivery.

DevOps & automation

Linux, Docker, Terraform, Ansible, GitLab CI/CD, monitoring, networking, virtualization and reproducible environments.

Selected projects

JobRunner

A controlled execution and monitoring platform for predefined Docker-based jobs with live logs, PostgreSQL-backed history, lifecycle management and observability.

FastAPIDockerPostgreSQLGrafana

Scrapper

A Dockerized public-data collection component for Google Maps search results, structured output and execution metrics, prepared for controlled job execution workflows.

PythonPlaywrightDocker

Codex1

An infrastructure automation project showing a Terraform to Hyper-V to generated Ansible inventory to Dockerized Ansible workflow for reproducible lab environments.

TerraformAnsibleHyper-V

AI-Journey

An engineering journal and operating record for AI-assisted delivery: RFCs, Codex CLI handoffs, Fast Bootstrap, session exports, Git history, review notes and human validation.

RFCsGitCodex CLIReview

LGTM Observability

A central Prometheus, Loki and Grafana stack that grew from GitLab monitoring into shared observability for applications and infrastructure.

PrometheusLokiGrafanaTerraform

Acer Aspire One 725 Lab

A legacy hardware lab for Debian, Home Assistant, kiosk experiments and battery/EC investigation with AI-assisted troubleshooting.

DebianACPIFirmwareHome Assistant

AI Journey

ChatGPT
Manual collaboration

Prompts, generated files and iterative technical work.

Git
Safety and reproducibility

Version control became essential after repeated AI-generated changes occasionally broke working code.

gpt_bot
My own automation layer

I experimented with OpenAI API, prompt history and automatic file updates committed to Git.

Codex
Agent working directly with repositories

The workflow shifted from receiving code to delegating bounded implementation tasks in real repositories.

RFC workflow
Architecture -> task -> implementation -> verification

ChatGPT prepares RFCs, Codex CLI works in Git, tests and validation run, sanitized session reports return for independent review, and the next RFC corrects course.

Handoff runner
Repeatable local execution

Fast Bootstrap, declared repositories, session metadata and export tooling make local Codex runs auditable instead of one-off chat experiments.

Case studies

AI-assisted delivery

Codex CLI workflow

Built a local RFC runner around explicit repositories, Fast Bootstrap, safe SSH/Git assumptions, sanitized session exports and reviewable return packages.

Production observability

Personal site monitoring

Moved monitoring into the site repository: Nginx JSON logs, Grafana Alloy, Loki delivery, log rotation, provisionable dashboards and GeoIP enrichment.

System boundary lesson

JobRunner integration checks

Used an Nginx/Prometheus regression to strengthen the workflow: verify the requested function and the neighbouring paths that depended on old assumptions.

Hardware troubleshooting

Legacy laptop recovery

Combined Debian administration, conservative battery testing, ACPI/EC analysis and firmware evidence to repurpose old hardware safely.

Core technologies

LinuxDockerDocker ComposeTerraformAnsible GitLabCI/CDPythonBashPowerShell NginxPrometheusLokiGrafanaProxmox Hyper-VWireGuardNetworkingChatGPTCodex

Let's work together

I am interested in roles focused on building new systems, modernizing existing projects and applying reviewed AI-assisted engineering to real infrastructure and software.